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

Dataset: Open Web Text

Neuron 1959 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: 4.7945. Min Range: -4.7945

Max Act: 4.7945. Min Act: -0.1700

Data Index: 1690055 (Open Web Text)

Max Activating Token Index: 702

Text #1

Max Range: 4.7945. Min Range: -4.7945

Max Act: 4.7312. Min Act: -0.1700

Data Index: 8249003 (Open Web Text)

Max Activating Token Index: 1015

Text #2

Max Range: 4.7945. Min Range: -4.7945

Max Act: 4.6014. Min Act: -0.1700

Data Index: 3109957 (Open Web Text)

Max Activating Token Index: 612

Text #3

Max Range: 4.7945. Min Range: -4.7945

Max Act: 4.5458. Min Act: -0.1700

Data Index: 5270946 (Open Web Text)

Max Activating Token Index: 440

Text #4

Max Range: 4.7945. Min Range: -4.7945

Max Act: 4.4877. Min Act: -0.1700

Data Index: 6837880 (Open Web Text)

Max Activating Token Index: 108

Text #5

Max Range: 4.7945. Min Range: -4.7945

Max Act: 4.4406. Min Act: -0.1700

Data Index: 2539833 (Open Web Text)

Max Activating Token Index: 672

Text #6

Max Range: 4.7945. Min Range: -4.7945

Max Act: 4.4411. Min Act: -0.1700

Data Index: 3041661 (Open Web Text)

Max Activating Token Index: 784

Text #7

Max Range: 4.7945. Min Range: -4.7945

Max Act: 4.4473. Min Act: -0.1700

Data Index: 1547081 (Open Web Text)

Max Activating Token Index: 663

Text #8

Max Range: 4.7945. Min Range: -4.7945

Max Act: 4.3890. Min Act: -0.1700

Data Index: 2575550 (Open Web Text)

Max Activating Token Index: 588

Text #9

Max Range: 4.7945. Min Range: -4.7945

Max Act: 4.3805. Min Act: -0.1700

Data Index: 8823468 (Open Web Text)

Max Activating Token Index: 327

Text #10

Max Range: 4.7945. Min Range: -4.7945

Max Act: 4.4375. Min Act: -0.1700

Data Index: 1927938 (Open Web Text)

Max Activating Token Index: 298

Text #11

Max Range: 4.7945. Min Range: -4.7945

Max Act: 4.3770. Min Act: -0.1700

Data Index: 3349853 (Open Web Text)

Max Activating Token Index: 271

Text #12

Max Range: 4.7945. Min Range: -4.7945

Max Act: 4.4122. Min Act: -0.1700

Data Index: 3273147 (Open Web Text)

Max Activating Token Index: 524

Text #13

Max Range: 4.7945. Min Range: -4.7945

Max Act: 4.3357. Min Act: -0.1700

Data Index: 5204031 (Open Web Text)

Max Activating Token Index: 754

Text #14

Max Range: 4.7945. Min Range: -4.7945

Max Act: 4.3376. Min Act: -0.1700

Data Index: 6421258 (Open Web Text)

Max Activating Token Index: 909

Text #15

Max Range: 4.7945. Min Range: -4.7945

Max Act: 4.3384. Min Act: -0.1700

Data Index: 4504183 (Open Web Text)

Max Activating Token Index: 105

Text #16

Max Range: 4.7945. Min Range: -4.7945

Max Act: 4.3441. Min Act: -0.1700

Data Index: 1150256 (Open Web Text)

Max Activating Token Index: 715

Text #17

Max Range: 4.7945. Min Range: -4.7945

Max Act: 4.3379. Min Act: -0.1700

Data Index: 1969962 (Open Web Text)

Max Activating Token Index: 572

Text #18

Max Range: 4.7945. Min Range: -4.7945

Max Act: 4.3288. Min Act: -0.1700

Data Index: 1902190 (Open Web Text)

Max Activating Token Index: 534

Text #19

Max Range: 4.7945. Min Range: -4.7945

Max Act: 4.3138. Min Act: -0.1700

Data Index: 778464 (Open Web Text)

Max Activating Token Index: 266