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

Dataset: Open Web Text

Neuron 2364 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: 3.2269. Min Range: -3.2269

Max Act: 3.2269. Min Act: -0.1700

Data Index: 2541241 (Open Web Text)

Max Activating Token Index: 328

Text #1

Max Range: 3.2269. Min Range: -3.2269

Max Act: 3.1808. Min Act: -0.1700

Data Index: 7548663 (Open Web Text)

Max Activating Token Index: 1004

Text #2

Max Range: 3.2269. Min Range: -3.2269

Max Act: 3.1712. Min Act: -0.1700

Data Index: 5017602 (Open Web Text)

Max Activating Token Index: 834

Text #3

Max Range: 3.2269. Min Range: -3.2269

Max Act: 3.1851. Min Act: -0.1700

Data Index: 47752 (Open Web Text)

Max Activating Token Index: 250

Text #4

Max Range: 3.2269. Min Range: -3.2269

Max Act: 3.1443. Min Act: -0.1700

Data Index: 1619422 (Open Web Text)

Max Activating Token Index: 987

Text #5

Max Range: 3.2269. Min Range: -3.2269

Max Act: 3.1343. Min Act: -0.1700

Data Index: 7192391 (Open Web Text)

Max Activating Token Index: 622

Text #6

Max Range: 3.2269. Min Range: -3.2269

Max Act: 3.1646. Min Act: -0.1700

Data Index: 6720807 (Open Web Text)

Max Activating Token Index: 732

Text #7

Max Range: 3.2269. Min Range: -3.2269

Max Act: 3.1363. Min Act: -0.1700

Data Index: 6983468 (Open Web Text)

Max Activating Token Index: 414

Text #8

Max Range: 3.2269. Min Range: -3.2269

Max Act: 3.1189. Min Act: -0.1700

Data Index: 3370907 (Open Web Text)

Max Activating Token Index: 606

Text #9

Max Range: 3.2269. Min Range: -3.2269

Max Act: 3.1383. Min Act: -0.1700

Data Index: 6270646 (Open Web Text)

Max Activating Token Index: 405

Text #10

Max Range: 3.2269. Min Range: -3.2269

Max Act: 3.1557. Min Act: -0.1700

Data Index: 5798377 (Open Web Text)

Max Activating Token Index: 615

Text #11

Max Range: 3.2269. Min Range: -3.2269

Max Act: 3.1381. Min Act: -0.1700

Data Index: 3044629 (Open Web Text)

Max Activating Token Index: 339

Text #12

Max Range: 3.2269. Min Range: -3.2269

Max Act: 3.1321. Min Act: -0.1700

Data Index: 1166466 (Open Web Text)

Max Activating Token Index: 97

Text #13

Max Range: 3.2269. Min Range: -3.2269

Max Act: 3.1378. Min Act: -0.1700

Data Index: 1902257 (Open Web Text)

Max Activating Token Index: 10

Text #14

Max Range: 3.2269. Min Range: -3.2269

Max Act: 3.1097. Min Act: -0.1700

Data Index: 7866103 (Open Web Text)

Max Activating Token Index: 958

Text #15

Max Range: 3.2269. Min Range: -3.2269

Max Act: 3.1597. Min Act: -0.1700

Data Index: 8525331 (Open Web Text)

Max Activating Token Index: 1017

Text #16

Max Range: 3.2269. Min Range: -3.2269

Max Act: 3.1153. Min Act: -0.1700

Data Index: 771653 (Open Web Text)

Max Activating Token Index: 505

Text #17

Max Range: 3.2269. Min Range: -3.2269

Max Act: 3.1068. Min Act: -0.1700

Data Index: 3370903 (Open Web Text)

Max Activating Token Index: 826

Text #18

Max Range: 3.2269. Min Range: -3.2269

Max Act: 3.1090. Min Act: -0.1700

Data Index: 4191805 (Open Web Text)

Max Activating Token Index: 974

Text #19

Max Range: 3.2269. Min Range: -3.2269

Max Act: 3.1286. Min Act: -0.1700

Data Index: 1692917 (Open Web Text)

Max Activating Token Index: 614