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

Dataset: Open Web Text

Neuron 1910 in Layer 1

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: 0.0376. Min Range: -0.0376

Max Act: 0.0334. Min Act: -0.1657

Data Index: 4915616 (Open Web Text)

Max Activating Token Index: 609

Text #1

Max Range: 0.0376. Min Range: -0.0376

Max Act: 0.0376. Min Act: -0.1679

Data Index: 7993739 (Open Web Text)

Max Activating Token Index: 580

Text #2

Max Range: 0.0376. Min Range: -0.0376

Max Act: 0.0298. Min Act: -0.1697

Data Index: 6600332 (Open Web Text)

Max Activating Token Index: 43

Text #3

Max Range: 0.0376. Min Range: -0.0376

Max Act: 0.0252. Min Act: -0.1676

Data Index: 6645535 (Open Web Text)

Max Activating Token Index: 7

Text #4

Max Range: 0.0376. Min Range: -0.0376

Max Act: 0.0245. Min Act: -0.1700

Data Index: 8133611 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 0.0376. Min Range: -0.0376

Max Act: 0.0242. Min Act: -0.1601

Data Index: 8564967 (Open Web Text)

Max Activating Token Index: 133

Text #6

Max Range: 0.0376. Min Range: -0.0376

Max Act: 0.0234. Min Act: -0.1700

Data Index: 3642892 (Open Web Text)

Max Activating Token Index: 6

Text #7

Max Range: 0.0376. Min Range: -0.0376

Max Act: 0.0175. Min Act: -0.1658

Data Index: 5164394 (Open Web Text)

Max Activating Token Index: 433

Text #8

Max Range: 0.0376. Min Range: -0.0376

Max Act: 0.0144. Min Act: -0.1673

Data Index: 8580346 (Open Web Text)

Max Activating Token Index: 11

Text #9

Max Range: 0.0376. Min Range: -0.0376

Max Act: 0.0178. Min Act: -0.1689

Data Index: 6805908 (Open Web Text)

Max Activating Token Index: 546

Text #10

Max Range: 0.0376. Min Range: -0.0376

Max Act: 0.0139. Min Act: -0.1602

Data Index: 4799196 (Open Web Text)

Max Activating Token Index: 282

Text #11

Max Range: 0.0376. Min Range: -0.0376

Max Act: 0.0102. Min Act: -0.1700

Data Index: 8796118 (Open Web Text)

Max Activating Token Index: 339

Text #12

Max Range: 0.0376. Min Range: -0.0376

Max Act: 0.0167. Min Act: -0.1621

Data Index: 8132669 (Open Web Text)

Max Activating Token Index: 940

Text #13

Max Range: 0.0376. Min Range: -0.0376

Max Act: 0.0104. Min Act: -0.1567

Data Index: 7981540 (Open Web Text)

Max Activating Token Index: 663

Text #14

Max Range: 0.0376. Min Range: -0.0376

Max Act: 0.0089. Min Act: -0.1604

Data Index: 7935627 (Open Web Text)

Max Activating Token Index: 481

Text #15

Max Range: 0.0376. Min Range: -0.0376

Max Act: 0.0040. Min Act: -0.1645

Data Index: 4235295 (Open Web Text)

Max Activating Token Index: 104

Text #16

Max Range: 0.0376. Min Range: -0.0376

Max Act: 0.0050. Min Act: -0.1697

Data Index: 6327857 (Open Web Text)

Max Activating Token Index: 749

Text #17

Max Range: 0.0376. Min Range: -0.0376

Max Act: 0.0029. Min Act: -0.1693

Data Index: 4017199 (Open Web Text)

Max Activating Token Index: 989

Text #18

Max Range: 0.0376. Min Range: -0.0376

Max Act: -0.0004. Min Act: -0.1700

Data Index: 4208905 (Open Web Text)

Max Activating Token Index: 81

Text #19

Max Range: 0.0376. Min Range: -0.0376

Max Act: 0.0063. Min Act: -0.1669

Data Index: 1664636 (Open Web Text)

Max Activating Token Index: 104