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

Dataset: Open Web Text

Neuron 1647 in Layer 4

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: 3.0538. Min Range: -3.0538

Max Act: 3.0527. Min Act: -0.1700

Data Index: 6569839 (Open Web Text)

Max Activating Token Index: 54

Text #1

Max Range: 3.0538. Min Range: -3.0538

Max Act: 3.0538. Min Act: -0.1700

Data Index: 2607585 (Open Web Text)

Max Activating Token Index: 181

Text #2

Max Range: 3.0538. Min Range: -3.0538

Max Act: 3.0491. Min Act: -0.1700

Data Index: 6792199 (Open Web Text)

Max Activating Token Index: 904

Text #3

Max Range: 3.0538. Min Range: -3.0538

Max Act: 3.0278. Min Act: -0.1700

Data Index: 202450 (Open Web Text)

Max Activating Token Index: 49

Text #4

Max Range: 3.0538. Min Range: -3.0538

Max Act: 2.9561. Min Act: -0.1700

Data Index: 2156853 (Open Web Text)

Max Activating Token Index: 402

Text #5

Max Range: 3.0538. Min Range: -3.0538

Max Act: 2.9712. Min Act: -0.1700

Data Index: 3068774 (Open Web Text)

Max Activating Token Index: 421

Text #6

Max Range: 3.0538. Min Range: -3.0538

Max Act: 2.9247. Min Act: -0.1700

Data Index: 2665587 (Open Web Text)

Max Activating Token Index: 221

Text #7

Max Range: 3.0538. Min Range: -3.0538

Max Act: 2.9623. Min Act: -0.1700

Data Index: 3305939 (Open Web Text)

Max Activating Token Index: 148

Text #8

Max Range: 3.0538. Min Range: -3.0538

Max Act: 2.9176. Min Act: -0.1700

Data Index: 7591496 (Open Web Text)

Max Activating Token Index: 58

Text #9

Max Range: 3.0538. Min Range: -3.0538

Max Act: 2.9396. Min Act: -0.1700

Data Index: 3390925 (Open Web Text)

Max Activating Token Index: 537

Text #10

Max Range: 3.0538. Min Range: -3.0538

Max Act: 2.9337. Min Act: -0.1700

Data Index: 5749494 (Open Web Text)

Max Activating Token Index: 170

Text #11

Max Range: 3.0538. Min Range: -3.0538

Max Act: 2.9564. Min Act: -0.1700

Data Index: 8367334 (Open Web Text)

Max Activating Token Index: 378

Text #12

Max Range: 3.0538. Min Range: -3.0538

Max Act: 2.9345. Min Act: -0.1700

Data Index: 1418468 (Open Web Text)

Max Activating Token Index: 160

Text #13

Max Range: 3.0538. Min Range: -3.0538

Max Act: 2.9272. Min Act: -0.1700

Data Index: 4144513 (Open Web Text)

Max Activating Token Index: 1004

Text #14

Max Range: 3.0538. Min Range: -3.0538

Max Act: 2.9415. Min Act: -0.1700

Data Index: 3474676 (Open Web Text)

Max Activating Token Index: 848

Text #15

Max Range: 3.0538. Min Range: -3.0538

Max Act: 2.9166. Min Act: -0.1700

Data Index: 2217305 (Open Web Text)

Max Activating Token Index: 425

Text #16

Max Range: 3.0538. Min Range: -3.0538

Max Act: 2.8966. Min Act: -0.1700

Data Index: 766773 (Open Web Text)

Max Activating Token Index: 754

Text #17

Max Range: 3.0538. Min Range: -3.0538

Max Act: 2.9129. Min Act: -0.1700

Data Index: 3779055 (Open Web Text)

Max Activating Token Index: 412

Text #18

Max Range: 3.0538. Min Range: -3.0538

Max Act: 2.8806. Min Act: -0.1700

Data Index: 6904027 (Open Web Text)

Max Activating Token Index: 222

Text #19

Max Range: 3.0538. Min Range: -3.0538

Max Act: 2.9164. Min Act: -0.1700

Data Index: 1641287 (Open Web Text)

Max Activating Token Index: 970