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

Dataset: Open Web Text

Neuron 1821 in Layer 0

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: 3.5427. Min Range: -3.5427

Max Act: 3.5427. Min Act: -0.1700

Data Index: 3991564 (Open Web Text)

Max Activating Token Index: 94

Text #1

Max Range: 3.5427. Min Range: -3.5427

Max Act: 3.5114. Min Act: -0.1700

Data Index: 724162 (Open Web Text)

Max Activating Token Index: 628

Text #2

Max Range: 3.5427. Min Range: -3.5427

Max Act: 3.4158. Min Act: -0.1700

Data Index: 7447027 (Open Web Text)

Max Activating Token Index: 1006

Text #3

Max Range: 3.5427. Min Range: -3.5427

Max Act: 3.4123. Min Act: -0.1700

Data Index: 8028280 (Open Web Text)

Max Activating Token Index: 754

Text #4

Max Range: 3.5427. Min Range: -3.5427

Max Act: 3.4104. Min Act: -0.1700

Data Index: 8409664 (Open Web Text)

Max Activating Token Index: 920

Text #5

Max Range: 3.5427. Min Range: -3.5427

Max Act: 3.3929. Min Act: -0.1700

Data Index: 6104377 (Open Web Text)

Max Activating Token Index: 805

Text #6

Max Range: 3.5427. Min Range: -3.5427

Max Act: 3.4168. Min Act: -0.1700

Data Index: 8641958 (Open Web Text)

Max Activating Token Index: 791

Text #7

Max Range: 3.5427. Min Range: -3.5427

Max Act: 3.3946. Min Act: -0.1700

Data Index: 2024231 (Open Web Text)

Max Activating Token Index: 977

Text #8

Max Range: 3.5427. Min Range: -3.5427

Max Act: 3.4085. Min Act: -0.1700

Data Index: 5221679 (Open Web Text)

Max Activating Token Index: 797

Text #9

Max Range: 3.5427. Min Range: -3.5427

Max Act: 3.3715. Min Act: -0.1700

Data Index: 2278833 (Open Web Text)

Max Activating Token Index: 726

Text #10

Max Range: 3.5427. Min Range: -3.5427

Max Act: 3.3561. Min Act: -0.1700

Data Index: 3600668 (Open Web Text)

Max Activating Token Index: 580

Text #11

Max Range: 3.5427. Min Range: -3.5427

Max Act: 3.3639. Min Act: -0.1700

Data Index: 7836543 (Open Web Text)

Max Activating Token Index: 890

Text #12

Max Range: 3.5427. Min Range: -3.5427

Max Act: 3.3203. Min Act: -0.1700

Data Index: 7307696 (Open Web Text)

Max Activating Token Index: 252

Text #13

Max Range: 3.5427. Min Range: -3.5427

Max Act: 3.3001. Min Act: -0.1700

Data Index: 1467295 (Open Web Text)

Max Activating Token Index: 952

Text #14

Max Range: 3.5427. Min Range: -3.5427

Max Act: 3.3264. Min Act: -0.1700

Data Index: 2262899 (Open Web Text)

Max Activating Token Index: 528

Text #15

Max Range: 3.5427. Min Range: -3.5427

Max Act: 3.3570. Min Act: -0.1700

Data Index: 3429396 (Open Web Text)

Max Activating Token Index: 744

Text #16

Max Range: 3.5427. Min Range: -3.5427

Max Act: 3.3140. Min Act: -0.1700

Data Index: 5110429 (Open Web Text)

Max Activating Token Index: 111

Text #17

Max Range: 3.5427. Min Range: -3.5427

Max Act: 3.3149. Min Act: -0.1700

Data Index: 2076522 (Open Web Text)

Max Activating Token Index: 1011

Text #18

Max Range: 3.5427. Min Range: -3.5427

Max Act: 3.3147. Min Act: -0.1700

Data Index: 6541588 (Open Web Text)

Max Activating Token Index: 632

Text #19

Max Range: 3.5427. Min Range: -3.5427

Max Act: 3.3075. Min Act: -0.1700

Data Index: 2048082 (Open Web Text)

Max Activating Token Index: 233