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

Dataset: Open Web Text

Neuron 2678 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: 1.0511. Min Range: -1.0511

Max Act: 1.0511. Min Act: -0.1700

Data Index: 8779971 (Open Web Text)

Max Activating Token Index: 66

Text #1

Max Range: 1.0511. Min Range: -1.0511

Max Act: 1.0247. Min Act: -0.1700

Data Index: 6345362 (Open Web Text)

Max Activating Token Index: 55

Text #2

Max Range: 1.0511. Min Range: -1.0511

Max Act: 0.9971. Min Act: -0.1700

Data Index: 5460422 (Open Web Text)

Max Activating Token Index: 51

Text #3

Max Range: 1.0511. Min Range: -1.0511

Max Act: 1.0112. Min Act: -0.1700

Data Index: 7123761 (Open Web Text)

Max Activating Token Index: 78

Text #4

Max Range: 1.0511. Min Range: -1.0511

Max Act: 0.9795. Min Act: -0.1700

Data Index: 7817929 (Open Web Text)

Max Activating Token Index: 71

Text #5

Max Range: 1.0511. Min Range: -1.0511

Max Act: 0.9553. Min Act: -0.1700

Data Index: 3156579 (Open Web Text)

Max Activating Token Index: 63

Text #6

Max Range: 1.0511. Min Range: -1.0511

Max Act: 0.9367. Min Act: -0.1700

Data Index: 247148 (Open Web Text)

Max Activating Token Index: 59

Text #7

Max Range: 1.0511. Min Range: -1.0511

Max Act: 0.9490. Min Act: -0.1700

Data Index: 8658684 (Open Web Text)

Max Activating Token Index: 50

Text #8

Max Range: 1.0511. Min Range: -1.0511

Max Act: 0.9474. Min Act: -0.1700

Data Index: 3026800 (Open Web Text)

Max Activating Token Index: 68

Text #9

Max Range: 1.0511. Min Range: -1.0511

Max Act: 0.9346. Min Act: -0.1700

Data Index: 8324886 (Open Web Text)

Max Activating Token Index: 77

Text #10

Max Range: 1.0511. Min Range: -1.0511

Max Act: 0.9352. Min Act: -0.1700

Data Index: 8438878 (Open Web Text)

Max Activating Token Index: 76

Text #11

Max Range: 1.0511. Min Range: -1.0511

Max Act: 0.9384. Min Act: -0.1700

Data Index: 5312189 (Open Web Text)

Max Activating Token Index: 49

Text #12

Max Range: 1.0511. Min Range: -1.0511

Max Act: 0.9296. Min Act: -0.1700

Data Index: 3490484 (Open Web Text)

Max Activating Token Index: 75

Text #13

Max Range: 1.0511. Min Range: -1.0511

Max Act: 0.9184. Min Act: -0.1700

Data Index: 4930210 (Open Web Text)

Max Activating Token Index: 61

Text #14

Max Range: 1.0511. Min Range: -1.0511

Max Act: 0.9127. Min Act: -0.1700

Data Index: 1978265 (Open Web Text)

Max Activating Token Index: 88

Text #15

Max Range: 1.0511. Min Range: -1.0511

Max Act: 0.9069. Min Act: -0.1700

Data Index: 749024 (Open Web Text)

Max Activating Token Index: 63

Text #16

Max Range: 1.0511. Min Range: -1.0511

Max Act: 0.9092. Min Act: -0.1700

Data Index: 4032061 (Open Web Text)

Max Activating Token Index: 70

Text #17

Max Range: 1.0511. Min Range: -1.0511

Max Act: 0.9016. Min Act: -0.1700

Data Index: 4599428 (Open Web Text)

Max Activating Token Index: 55

Text #18

Max Range: 1.0511. Min Range: -1.0511

Max Act: 0.9138. Min Act: -0.1700

Data Index: 16824 (Open Web Text)

Max Activating Token Index: 73

Text #19

Max Range: 1.0511. Min Range: -1.0511

Max Act: 0.9019. Min Act: -0.1700

Data Index: 4713128 (Open Web Text)

Max Activating Token Index: 64