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

Dataset: Open Web Text

Neuron 41 in Layer 6

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: 5.0566. Min Range: -5.0566

Max Act: 5.0566. Min Act: -0.1700

Data Index: 6199216 (Open Web Text)

Max Activating Token Index: 920

Text #1

Max Range: 5.0566. Min Range: -5.0566

Max Act: 5.0335. Min Act: -0.1700

Data Index: 6417745 (Open Web Text)

Max Activating Token Index: 91

Text #2

Max Range: 5.0566. Min Range: -5.0566

Max Act: 5.0380. Min Act: -0.1700

Data Index: 5179288 (Open Web Text)

Max Activating Token Index: 579

Text #3

Max Range: 5.0566. Min Range: -5.0566

Max Act: 4.9948. Min Act: -0.1700

Data Index: 1975806 (Open Web Text)

Max Activating Token Index: 596

Text #4

Max Range: 5.0566. Min Range: -5.0566

Max Act: 4.9903. Min Act: -0.1700

Data Index: 2245619 (Open Web Text)

Max Activating Token Index: 379

Text #5

Max Range: 5.0566. Min Range: -5.0566

Max Act: 5.0035. Min Act: -0.1700

Data Index: 6406292 (Open Web Text)

Max Activating Token Index: 121

Text #6

Max Range: 5.0566. Min Range: -5.0566

Max Act: 4.9654. Min Act: -0.1700

Data Index: 5873157 (Open Web Text)

Max Activating Token Index: 845

Text #7

Max Range: 5.0566. Min Range: -5.0566

Max Act: 4.9916. Min Act: -0.1700

Data Index: 3206354 (Open Web Text)

Max Activating Token Index: 470

Text #8

Max Range: 5.0566. Min Range: -5.0566

Max Act: 4.9918. Min Act: -0.1700

Data Index: 7186755 (Open Web Text)

Max Activating Token Index: 721

Text #9

Max Range: 5.0566. Min Range: -5.0566

Max Act: 4.9461. Min Act: -0.1700

Data Index: 4064721 (Open Web Text)

Max Activating Token Index: 248

Text #10

Max Range: 5.0566. Min Range: -5.0566

Max Act: 4.9318. Min Act: -0.1700

Data Index: 7878432 (Open Web Text)

Max Activating Token Index: 133

Text #11

Max Range: 5.0566. Min Range: -5.0566

Max Act: 4.8918. Min Act: -0.1700

Data Index: 3783135 (Open Web Text)

Max Activating Token Index: 423

Text #12

Max Range: 5.0566. Min Range: -5.0566

Max Act: 4.8861. Min Act: -0.1700

Data Index: 2607569 (Open Web Text)

Max Activating Token Index: 970

Text #13

Max Range: 5.0566. Min Range: -5.0566

Max Act: 4.9110. Min Act: -0.1700

Data Index: 5712426 (Open Web Text)

Max Activating Token Index: 991

Text #14

Max Range: 5.0566. Min Range: -5.0566

Max Act: 4.8807. Min Act: -0.1700

Data Index: 8207458 (Open Web Text)

Max Activating Token Index: 980

Text #15

Max Range: 5.0566. Min Range: -5.0566

Max Act: 4.9082. Min Act: -0.1700

Data Index: 2501101 (Open Web Text)

Max Activating Token Index: 505

Text #16

Max Range: 5.0566. Min Range: -5.0566

Max Act: 4.9033. Min Act: -0.1700

Data Index: 5169665 (Open Web Text)

Max Activating Token Index: 148

Text #17

Max Range: 5.0566. Min Range: -5.0566

Max Act: 4.8838. Min Act: -0.1700

Data Index: 5727643 (Open Web Text)

Max Activating Token Index: 987

Text #18

Max Range: 5.0566. Min Range: -5.0566

Max Act: 4.8680. Min Act: -0.1700

Data Index: 623891 (Open Web Text)

Max Activating Token Index: 839

Text #19

Max Range: 5.0566. Min Range: -5.0566

Max Act: 4.8863. Min Act: -0.1700

Data Index: 1103425 (Open Web Text)

Max Activating Token Index: 211