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

Dataset: Open Web Text

Neuron 1164 in Layer 3

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: 3.6511. Min Range: -3.6511

Max Act: 3.6511. Min Act: -0.1700

Data Index: 810935 (Open Web Text)

Max Activating Token Index: 772

Text #1

Max Range: 3.6511. Min Range: -3.6511

Max Act: 3.5444. Min Act: -0.1700

Data Index: 5167483 (Open Web Text)

Max Activating Token Index: 201

Text #2

Max Range: 3.6511. Min Range: -3.6511

Max Act: 3.5211. Min Act: -0.1700

Data Index: 128975 (Open Web Text)

Max Activating Token Index: 134

Text #3

Max Range: 3.6511. Min Range: -3.6511

Max Act: 3.4546. Min Act: -0.1700

Data Index: 3849471 (Open Web Text)

Max Activating Token Index: 102

Text #4

Max Range: 3.6511. Min Range: -3.6511

Max Act: 3.4248. Min Act: -0.1700

Data Index: 7980878 (Open Web Text)

Max Activating Token Index: 917

Text #5

Max Range: 3.6511. Min Range: -3.6511

Max Act: 3.4036. Min Act: -0.1700

Data Index: 780317 (Open Web Text)

Max Activating Token Index: 766

Text #6

Max Range: 3.6511. Min Range: -3.6511

Max Act: 3.4287. Min Act: -0.1700

Data Index: 3438028 (Open Web Text)

Max Activating Token Index: 373

Text #7

Max Range: 3.6511. Min Range: -3.6511

Max Act: 3.3456. Min Act: -0.1700

Data Index: 4613519 (Open Web Text)

Max Activating Token Index: 475

Text #8

Max Range: 3.6511. Min Range: -3.6511

Max Act: 3.3354. Min Act: -0.1700

Data Index: 1746247 (Open Web Text)

Max Activating Token Index: 167

Text #9

Max Range: 3.6511. Min Range: -3.6511

Max Act: 3.3159. Min Act: -0.1700

Data Index: 3246132 (Open Web Text)

Max Activating Token Index: 809

Text #10

Max Range: 3.6511. Min Range: -3.6511

Max Act: 3.3084. Min Act: -0.1700

Data Index: 3119843 (Open Web Text)

Max Activating Token Index: 749

Text #11

Max Range: 3.6511. Min Range: -3.6511

Max Act: 3.2946. Min Act: -0.1700

Data Index: 5320446 (Open Web Text)

Max Activating Token Index: 565

Text #12

Max Range: 3.6511. Min Range: -3.6511

Max Act: 3.2928. Min Act: -0.1700

Data Index: 1060640 (Open Web Text)

Max Activating Token Index: 454

Text #13

Max Range: 3.6511. Min Range: -3.6511

Max Act: 3.2565. Min Act: -0.1700

Data Index: 3275435 (Open Web Text)

Max Activating Token Index: 93

Text #14

Max Range: 3.6511. Min Range: -3.6511

Max Act: 3.2948. Min Act: -0.1700

Data Index: 2515789 (Open Web Text)

Max Activating Token Index: 458

Text #15

Max Range: 3.6511. Min Range: -3.6511

Max Act: 3.2373. Min Act: -0.1700

Data Index: 41725 (Open Web Text)

Max Activating Token Index: 959

Text #16

Max Range: 3.6511. Min Range: -3.6511

Max Act: 3.2548. Min Act: -0.1700

Data Index: 5021341 (Open Web Text)

Max Activating Token Index: 194

Text #17

Max Range: 3.6511. Min Range: -3.6511

Max Act: 3.2111. Min Act: -0.1700

Data Index: 7471478 (Open Web Text)

Max Activating Token Index: 399

Text #18

Max Range: 3.6511. Min Range: -3.6511

Max Act: 3.2473. Min Act: -0.1700

Data Index: 3204205 (Open Web Text)

Max Activating Token Index: 950

Text #19

Max Range: 3.6511. Min Range: -3.6511

Max Act: 3.2477. Min Act: -0.1700

Data Index: 5084218 (Open Web Text)

Max Activating Token Index: 852