Transformer Explainer: Interactive Learning of Text-Generative Models

Transformer Explainer is an interactive visualization tool designed to help anyone learn how Transformer-based models like GPT work. It runs a live GPT-2 model right in your browser, allowing you to experiment with your own text and observe in real time how internal components and operations of the Transformer work together to predict the next tokens. Try Transformer Explainer at http://poloclub.github.io/transformer-explainer and watch a demo video on YouTube https://youtu.be/ECR4oAwocjs .

transformer-explainer.mp4
🚀 Live Demo	📺 Demo Video

Research Paper

Transformer Explainer: Interactive Learning of Text-Generative Models. Aeree Cho, Grace C. Kim, Alexander Karpekov, Alec Helbling, Zijie J. Wang, Seongmin Lee, Benjamin Hoover, Duen Horng Chau. Poster, IEEE VIS 2024.

How to run locally

Prerequisites

Node.js 20 or higher
NPM

Steps

git clone https://github.com/poloclub/transformer-explainer.git
cd transformer-explainer
npm install
npm run dev

Then, on your web browser, access http://localhost:5173.

Credits

Transformer Explainer was created by Aeree Cho, Grace C. Kim, Alexander Karpekov, Alec Helbling, Jay Wang, Seongmin Lee, Benjamin Hoover, and Polo Chau at the Georgia Institute of Technology.

Citation

@article{cho2024transformer,
  title = {Transformer Explainer: Interactive Learning of Text-Generative Models},
  shorttitle = {Transformer Explainer},
  author = {Cho, Aeree and Kim, Grace C. and Karpekov, Alexander and Helbling, Alec and Wang, Zijie J. and Lee, Seongmin and Hoover, Benjamin and Chau, Duen Horng},
  journal={IEEE VIS},
  year={2024}
}

License

The software is available under the MIT License.

Contact

If you have any questions, feel free to open an issue or contact Aeree Cho or any of the contributors listed above.

xuyongfu/transformer-explainer