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

Dataset: Open Web Text

Neuron 971 in Layer 1

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: 3.7484. Min Range: -3.7484

Max Act: 3.7484. Min Act: -0.1700

Data Index: 4122329 (Open Web Text)

Max Activating Token Index: 66

Text #1

Max Range: 3.7484. Min Range: -3.7484

Max Act: 3.7384. Min Act: -0.1700

Data Index: 7912755 (Open Web Text)

Max Activating Token Index: 36

Text #2

Max Range: 3.7484. Min Range: -3.7484

Max Act: 3.6821. Min Act: -0.1700

Data Index: 7017732 (Open Web Text)

Max Activating Token Index: 265

Text #3

Max Range: 3.7484. Min Range: -3.7484

Max Act: 3.7022. Min Act: -0.1700

Data Index: 5575232 (Open Web Text)

Max Activating Token Index: 58

Text #4

Max Range: 3.7484. Min Range: -3.7484

Max Act: 3.6698. Min Act: -0.1700

Data Index: 1278344 (Open Web Text)

Max Activating Token Index: 99

Text #5

Max Range: 3.7484. Min Range: -3.7484

Max Act: 3.6766. Min Act: -0.1700

Data Index: 3983828 (Open Web Text)

Max Activating Token Index: 115

Text #6

Max Range: 3.7484. Min Range: -3.7484

Max Act: 3.6391. Min Act: -0.1700

Data Index: 2194887 (Open Web Text)

Max Activating Token Index: 78

Text #7

Max Range: 3.7484. Min Range: -3.7484

Max Act: 3.6665. Min Act: -0.1700

Data Index: 1569591 (Open Web Text)

Max Activating Token Index: 55

Text #8

Max Range: 3.7484. Min Range: -3.7484

Max Act: 3.6352. Min Act: -0.1700

Data Index: 328529 (Open Web Text)

Max Activating Token Index: 486

Text #9

Max Range: 3.7484. Min Range: -3.7484

Max Act: 3.6090. Min Act: -0.1700

Data Index: 5784709 (Open Web Text)

Max Activating Token Index: 42

Text #10

Max Range: 3.7484. Min Range: -3.7484

Max Act: 3.6049. Min Act: -0.1700

Data Index: 448574 (Open Web Text)

Max Activating Token Index: 85

Text #11

Max Range: 3.7484. Min Range: -3.7484

Max Act: 3.6028. Min Act: -0.1700

Data Index: 8158658 (Open Web Text)

Max Activating Token Index: 62

Text #12

Max Range: 3.7484. Min Range: -3.7484

Max Act: 3.5735. Min Act: -0.1700

Data Index: 5935761 (Open Web Text)

Max Activating Token Index: 73

Text #13

Max Range: 3.7484. Min Range: -3.7484

Max Act: 3.5628. Min Act: -0.1700

Data Index: 7136199 (Open Web Text)

Max Activating Token Index: 46

Text #14

Max Range: 3.7484. Min Range: -3.7484

Max Act: 3.5834. Min Act: -0.1700

Data Index: 2581961 (Open Web Text)

Max Activating Token Index: 123

Text #15

Max Range: 3.7484. Min Range: -3.7484

Max Act: 3.5749. Min Act: -0.1700

Data Index: 6739647 (Open Web Text)

Max Activating Token Index: 42

Text #16

Max Range: 3.7484. Min Range: -3.7484

Max Act: 3.5406. Min Act: -0.1700

Data Index: 1509167 (Open Web Text)

Max Activating Token Index: 89

Text #17

Max Range: 3.7484. Min Range: -3.7484

Max Act: 3.5612. Min Act: -0.1700

Data Index: 4992382 (Open Web Text)

Max Activating Token Index: 140

Text #18

Max Range: 3.7484. Min Range: -3.7484

Max Act: 3.5335. Min Act: -0.1700

Data Index: 770203 (Open Web Text)

Max Activating Token Index: 34

Text #19

Max Range: 3.7484. Min Range: -3.7484

Max Act: 3.5242. Min Act: -0.1700

Data Index: 5382462 (Open Web Text)

Max Activating Token Index: 381