NeuroX: A Toolkit for Analyzing Individual Neurons in Neural Networks

  • Fahim Dalvi Hamad Bin Khalifa University
  • Avery Nortonsmith Massachusetts Institute of Technology
  • Anthony Bau Massachusetts Institute of Technology
  • Yonatan Belinkov Massachusetts Institute of Technology
  • Hassan Sajjad Hamad Bin Khalifa University
  • Nadir Durrani Hamad Bin Khalifa University
  • James Glass Massachusetts Institute of Technology

Abstract

We present a toolkit to facilitate the interpretation and understanding of neural network models. The toolkit provides several methods to identify salient neurons with respect to the model itself or an external task. A user can visualize selected neurons, ablate them to measure their effect on the model accuracy, and manipulate them to control the behavior of the model at the test time. Such an analysis has a potential to serve as a springboard in various research directions, such as understanding the model, better architectural choices, model distillation and controlling data biases. The toolkit is available for download.1

Published
2019-07-17
Section
Demonstration Track