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

Dataset: Open Web Text

Neuron 1106 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: 1.2870. Min Range: -1.2870

Max Act: 1.2816. Min Act: -0.1700

Data Index: 949110 (Open Web Text)

Max Activating Token Index: 365

Text #1

Max Range: 1.2870. Min Range: -1.2870

Max Act: 1.2771. Min Act: -0.1700

Data Index: 350618 (Open Web Text)

Max Activating Token Index: 710

Text #2

Max Range: 1.2870. Min Range: -1.2870

Max Act: 1.2870. Min Act: -0.1699

Data Index: 6230339 (Open Web Text)

Max Activating Token Index: 109

Text #3

Max Range: 1.2870. Min Range: -1.2870

Max Act: 1.2504. Min Act: -0.1700

Data Index: 2242987 (Open Web Text)

Max Activating Token Index: 59

Text #4

Max Range: 1.2870. Min Range: -1.2870

Max Act: 1.2453. Min Act: -0.1700

Data Index: 2918581 (Open Web Text)

Max Activating Token Index: 778

Text #5

Max Range: 1.2870. Min Range: -1.2870

Max Act: 1.2376. Min Act: -0.1700

Data Index: 5383111 (Open Web Text)

Max Activating Token Index: 57

Text #6

Max Range: 1.2870. Min Range: -1.2870

Max Act: 1.2352. Min Act: -0.1700

Data Index: 4969563 (Open Web Text)

Max Activating Token Index: 889

Text #7

Max Range: 1.2870. Min Range: -1.2870

Max Act: 1.2301. Min Act: -0.1700

Data Index: 5741304 (Open Web Text)

Max Activating Token Index: 55

Text #8

Max Range: 1.2870. Min Range: -1.2870

Max Act: 1.2373. Min Act: -0.1700

Data Index: 313348 (Open Web Text)

Max Activating Token Index: 385

Text #9

Max Range: 1.2870. Min Range: -1.2870

Max Act: 1.2324. Min Act: -0.1700

Data Index: 1640379 (Open Web Text)

Max Activating Token Index: 286

Text #10

Max Range: 1.2870. Min Range: -1.2870

Max Act: 1.2348. Min Act: -0.1700

Data Index: 7605510 (Open Web Text)

Max Activating Token Index: 656

Text #11

Max Range: 1.2870. Min Range: -1.2870

Max Act: 1.2330. Min Act: -0.1700

Data Index: 799834 (Open Web Text)

Max Activating Token Index: 316

Text #12

Max Range: 1.2870. Min Range: -1.2870

Max Act: 1.2387. Min Act: -0.1700

Data Index: 1392686 (Open Web Text)

Max Activating Token Index: 938

Text #13

Max Range: 1.2870. Min Range: -1.2870

Max Act: 1.2204. Min Act: -0.1700

Data Index: 3319244 (Open Web Text)

Max Activating Token Index: 132

Text #14

Max Range: 1.2870. Min Range: -1.2870

Max Act: 1.2159. Min Act: -0.1700

Data Index: 7925490 (Open Web Text)

Max Activating Token Index: 444

Text #15

Max Range: 1.2870. Min Range: -1.2870

Max Act: 1.2214. Min Act: -0.1700

Data Index: 1296342 (Open Web Text)

Max Activating Token Index: 930

Text #16

Max Range: 1.2870. Min Range: -1.2870

Max Act: 1.2105. Min Act: -0.1700

Data Index: 7157667 (Open Web Text)

Max Activating Token Index: 432

Text #17

Max Range: 1.2870. Min Range: -1.2870

Max Act: 1.2115. Min Act: -0.1700

Data Index: 299188 (Open Web Text)

Max Activating Token Index: 605

Text #18

Max Range: 1.2870. Min Range: -1.2870

Max Act: 1.2123. Min Act: -0.1700

Data Index: 1596940 (Open Web Text)

Max Activating Token Index: 85

Text #19

Max Range: 1.2870. Min Range: -1.2870

Max Act: 1.2203. Min Act: -0.1700

Data Index: 6593125 (Open Web Text)

Max Activating Token Index: 708