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

Dataset: Open Web Text

Neuron 652 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: 3.2461. Min Range: -3.2461

Max Act: 3.2461. Min Act: -0.1700

Data Index: 5923702 (Open Web Text)

Max Activating Token Index: 150

Text #1

Max Range: 3.2461. Min Range: -3.2461

Max Act: 3.2152. Min Act: -0.1700

Data Index: 6582997 (Open Web Text)

Max Activating Token Index: 174

Text #2

Max Range: 3.2461. Min Range: -3.2461

Max Act: 3.1941. Min Act: -0.1700

Data Index: 8792131 (Open Web Text)

Max Activating Token Index: 645

Text #3

Max Range: 3.2461. Min Range: -3.2461

Max Act: 3.1937. Min Act: -0.1700

Data Index: 2984168 (Open Web Text)

Max Activating Token Index: 833

Text #4

Max Range: 3.2461. Min Range: -3.2461

Max Act: 3.1869. Min Act: -0.1700

Data Index: 2112164 (Open Web Text)

Max Activating Token Index: 728

Text #5

Max Range: 3.2461. Min Range: -3.2461

Max Act: 3.1569. Min Act: -0.1700

Data Index: 4067477 (Open Web Text)

Max Activating Token Index: 962

Text #6

Max Range: 3.2461. Min Range: -3.2461

Max Act: 3.1765. Min Act: -0.1700

Data Index: 6091944 (Open Web Text)

Max Activating Token Index: 129

Text #7

Max Range: 3.2461. Min Range: -3.2461

Max Act: 3.1777. Min Act: -0.1700

Data Index: 6756027 (Open Web Text)

Max Activating Token Index: 911

Text #8

Max Range: 3.2461. Min Range: -3.2461

Max Act: 3.1609. Min Act: -0.1700

Data Index: 5436327 (Open Web Text)

Max Activating Token Index: 821

Text #9

Max Range: 3.2461. Min Range: -3.2461

Max Act: 3.1403. Min Act: -0.1700

Data Index: 1793481 (Open Web Text)

Max Activating Token Index: 810

Text #10

Max Range: 3.2461. Min Range: -3.2461

Max Act: 3.1613. Min Act: -0.1700

Data Index: 3938336 (Open Web Text)

Max Activating Token Index: 163

Text #11

Max Range: 3.2461. Min Range: -3.2461

Max Act: 3.1496. Min Act: -0.1700

Data Index: 3856014 (Open Web Text)

Max Activating Token Index: 581

Text #12

Max Range: 3.2461. Min Range: -3.2461

Max Act: 3.1365. Min Act: -0.1700

Data Index: 7676127 (Open Web Text)

Max Activating Token Index: 733

Text #13

Max Range: 3.2461. Min Range: -3.2461

Max Act: 3.1228. Min Act: -0.1700

Data Index: 2657843 (Open Web Text)

Max Activating Token Index: 110

Text #14

Max Range: 3.2461. Min Range: -3.2461

Max Act: 3.1224. Min Act: -0.1700

Data Index: 2052025 (Open Web Text)

Max Activating Token Index: 232

Text #15

Max Range: 3.2461. Min Range: -3.2461

Max Act: 3.1308. Min Act: -0.1700

Data Index: 8826275 (Open Web Text)

Max Activating Token Index: 176

Text #16

Max Range: 3.2461. Min Range: -3.2461

Max Act: 3.1164. Min Act: -0.1700

Data Index: 1955509 (Open Web Text)

Max Activating Token Index: 58

Text #17

Max Range: 3.2461. Min Range: -3.2461

Max Act: 3.1146. Min Act: -0.1700

Data Index: 8446626 (Open Web Text)

Max Activating Token Index: 969

Text #18

Max Range: 3.2461. Min Range: -3.2461

Max Act: 3.1033. Min Act: -0.1700

Data Index: 5586765 (Open Web Text)

Max Activating Token Index: 805

Text #19

Max Range: 3.2461. Min Range: -3.2461

Max Act: 3.1211. Min Act: -0.1700

Data Index: 1022517 (Open Web Text)

Max Activating Token Index: 311