Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 2009 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 1.4395. Min Range: -1.4395

Max Act: 1.4395. Min Act: -0.1700

Data Index: 3223454 (Open Web Text)

Max Activating Token Index: 215

Text #1

Max Range: 1.4395. Min Range: -1.4395

Max Act: 1.4257. Min Act: -0.1699

Data Index: 5918133 (Open Web Text)

Max Activating Token Index: 287

Text #2

Max Range: 1.4395. Min Range: -1.4395

Max Act: 1.4323. Min Act: -0.1700

Data Index: 4459910 (Open Web Text)

Max Activating Token Index: 144

Text #3

Max Range: 1.4395. Min Range: -1.4395

Max Act: 1.4098. Min Act: -0.1700

Data Index: 937527 (Open Web Text)

Max Activating Token Index: 966

Text #4

Max Range: 1.4395. Min Range: -1.4395

Max Act: 1.3999. Min Act: -0.1700

Data Index: 6774530 (Open Web Text)

Max Activating Token Index: 414

Text #5

Max Range: 1.4395. Min Range: -1.4395

Max Act: 1.4139. Min Act: -0.1700

Data Index: 6102592 (Open Web Text)

Max Activating Token Index: 790

Text #6

Max Range: 1.4395. Min Range: -1.4395

Max Act: 1.3946. Min Act: -0.1700

Data Index: 2793279 (Open Web Text)

Max Activating Token Index: 602

Text #7

Max Range: 1.4395. Min Range: -1.4395

Max Act: 1.3860. Min Act: -0.1700

Data Index: 7261526 (Open Web Text)

Max Activating Token Index: 933

Text #8

Max Range: 1.4395. Min Range: -1.4395

Max Act: 1.4048. Min Act: -0.1696

Data Index: 5434233 (Open Web Text)

Max Activating Token Index: 153

Text #9

Max Range: 1.4395. Min Range: -1.4395

Max Act: 1.3898. Min Act: -0.1700

Data Index: 2632816 (Open Web Text)

Max Activating Token Index: 626

Text #10

Max Range: 1.4395. Min Range: -1.4395

Max Act: 1.3806. Min Act: -0.1699

Data Index: 4473918 (Open Web Text)

Max Activating Token Index: 316

Text #11

Max Range: 1.4395. Min Range: -1.4395

Max Act: 1.4027. Min Act: -0.1700

Data Index: 3111965 (Open Web Text)

Max Activating Token Index: 656

Text #12

Max Range: 1.4395. Min Range: -1.4395

Max Act: 1.3904. Min Act: -0.1691

Data Index: 6416939 (Open Web Text)

Max Activating Token Index: 960

Text #13

Max Range: 1.4395. Min Range: -1.4395

Max Act: 1.3905. Min Act: -0.1700

Data Index: 1444950 (Open Web Text)

Max Activating Token Index: 537

Text #14

Max Range: 1.4395. Min Range: -1.4395

Max Act: 1.3856. Min Act: -0.1700

Data Index: 1609748 (Open Web Text)

Max Activating Token Index: 861

Text #15

Max Range: 1.4395. Min Range: -1.4395

Max Act: 1.3847. Min Act: -0.1700

Data Index: 6081410 (Open Web Text)

Max Activating Token Index: 178

Text #16

Max Range: 1.4395. Min Range: -1.4395

Max Act: 1.3854. Min Act: -0.1700

Data Index: 6233714 (Open Web Text)

Max Activating Token Index: 496

Text #17

Max Range: 1.4395. Min Range: -1.4395

Max Act: 1.3714. Min Act: -0.1700

Data Index: 7135885 (Open Web Text)

Max Activating Token Index: 471

Text #18

Max Range: 1.4395. Min Range: -1.4395

Max Act: 1.3684. Min Act: -0.1697

Data Index: 285005 (Open Web Text)

Max Activating Token Index: 399

Text #19

Max Range: 1.4395. Min Range: -1.4395

Max Act: 1.3694. Min Act: -0.1698

Data Index: 2000272 (Open Web Text)

Max Activating Token Index: 693