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

Dataset: Open Web Text

Neuron 2066 in Layer 5

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: 3.8639. Min Range: -3.8639

Max Act: 3.8639. Min Act: -0.1700

Data Index: 2055143 (Open Web Text)

Max Activating Token Index: 671

Text #1

Max Range: 3.8639. Min Range: -3.8639

Max Act: 3.8591. Min Act: -0.1700

Data Index: 1299475 (Open Web Text)

Max Activating Token Index: 527

Text #2

Max Range: 3.8639. Min Range: -3.8639

Max Act: 3.8517. Min Act: -0.1700

Data Index: 3887271 (Open Web Text)

Max Activating Token Index: 414

Text #3

Max Range: 3.8639. Min Range: -3.8639

Max Act: 3.8473. Min Act: -0.1700

Data Index: 7997519 (Open Web Text)

Max Activating Token Index: 362

Text #4

Max Range: 3.8639. Min Range: -3.8639

Max Act: 3.8633. Min Act: -0.1700

Data Index: 5349979 (Open Web Text)

Max Activating Token Index: 283

Text #5

Max Range: 3.8639. Min Range: -3.8639

Max Act: 3.8109. Min Act: -0.1700

Data Index: 3268060 (Open Web Text)

Max Activating Token Index: 118

Text #6

Max Range: 3.8639. Min Range: -3.8639

Max Act: 3.8128. Min Act: -0.1700

Data Index: 2334728 (Open Web Text)

Max Activating Token Index: 28

Text #7

Max Range: 3.8639. Min Range: -3.8639

Max Act: 3.8141. Min Act: -0.1700

Data Index: 5063770 (Open Web Text)

Max Activating Token Index: 900

Text #8

Max Range: 3.8639. Min Range: -3.8639

Max Act: 3.8171. Min Act: -0.1700

Data Index: 2788158 (Open Web Text)

Max Activating Token Index: 191

Text #9

Max Range: 3.8639. Min Range: -3.8639

Max Act: 3.7917. Min Act: -0.1700

Data Index: 2712202 (Open Web Text)

Max Activating Token Index: 369

Text #10

Max Range: 3.8639. Min Range: -3.8639

Max Act: 3.7936. Min Act: -0.1700

Data Index: 1081351 (Open Web Text)

Max Activating Token Index: 314

Text #11

Max Range: 3.8639. Min Range: -3.8639

Max Act: 3.7923. Min Act: -0.1700

Data Index: 6826835 (Open Web Text)

Max Activating Token Index: 517

Text #12

Max Range: 3.8639. Min Range: -3.8639

Max Act: 3.7929. Min Act: -0.1700

Data Index: 2044361 (Open Web Text)

Max Activating Token Index: 723

Text #13

Max Range: 3.8639. Min Range: -3.8639

Max Act: 3.7750. Min Act: -0.1700

Data Index: 6721108 (Open Web Text)

Max Activating Token Index: 524

Text #14

Max Range: 3.8639. Min Range: -3.8639

Max Act: 3.7803. Min Act: -0.1700

Data Index: 907897 (Open Web Text)

Max Activating Token Index: 389

Text #15

Max Range: 3.8639. Min Range: -3.8639

Max Act: 3.7941. Min Act: -0.1700

Data Index: 373989 (Open Web Text)

Max Activating Token Index: 593

Text #16

Max Range: 3.8639. Min Range: -3.8639

Max Act: 3.8056. Min Act: -0.1700

Data Index: 2183428 (Open Web Text)

Max Activating Token Index: 439

Text #17

Max Range: 3.8639. Min Range: -3.8639

Max Act: 3.7695. Min Act: -0.1700

Data Index: 845905 (Open Web Text)

Max Activating Token Index: 415

Text #18

Max Range: 3.8639. Min Range: -3.8639

Max Act: 3.7394. Min Act: -0.1700

Data Index: 3399246 (Open Web Text)

Max Activating Token Index: 585

Text #19

Max Range: 3.8639. Min Range: -3.8639

Max Act: 3.7507. Min Act: -0.1700

Data Index: 3520546 (Open Web Text)

Max Activating Token Index: 359