< Prev | Home | Model | Random | Next >

Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer

Dataset: Open Web Text

Neuron 6351 in Layer 43

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')



Text #0

Max Range: 12.0726. Min Range: -12.0726

Max Act: 12.0726. Min Act: -0.1700

Data Index: 8063987 (Open Web Text)

Max Activating Token Index: 711

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 12.0726. Min Range: -12.0726

Max Act: 11.3226. Min Act: -0.1700

Data Index: 8483098 (Open Web Text)

Max Activating Token Index: 534

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 12.0726. Min Range: -12.0726

Max Act: 11.1976. Min Act: -0.1700

Data Index: 5078994 (Open Web Text)

Max Activating Token Index: 66

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 12.0726. Min Range: -12.0726

Max Act: 11.1976. Min Act: -0.1700

Data Index: 2025865 (Open Web Text)

Max Activating Token Index: 101

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 12.0726. Min Range: -12.0726

Max Act: 11.1976. Min Act: -0.1700

Data Index: 7875748 (Open Web Text)

Max Activating Token Index: 141

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 12.0726. Min Range: -12.0726

Max Act: 11.1351. Min Act: -0.1700

Data Index: 63330 (Open Web Text)

Max Activating Token Index: 386

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 12.0726. Min Range: -12.0726

Max Act: 11.1351. Min Act: -0.1699

Data Index: 1856787 (Open Web Text)

Max Activating Token Index: 599

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 12.0726. Min Range: -12.0726

Max Act: 11.0726. Min Act: -0.1700

Data Index: 3028200 (Open Web Text)

Max Activating Token Index: 782

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 12.0726. Min Range: -12.0726

Max Act: 11.0726. Min Act: -0.1700

Data Index: 3482482 (Open Web Text)

Max Activating Token Index: 890

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 12.0726. Min Range: -12.0726

Max Act: 11.0726. Min Act: -0.1700

Data Index: 7719612 (Open Web Text)

Max Activating Token Index: 106

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 12.0726. Min Range: -12.0726

Max Act: 10.9476. Min Act: -0.1700

Data Index: 7673767 (Open Web Text)

Max Activating Token Index: 171

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 12.0726. Min Range: -12.0726

Max Act: 11.0101. Min Act: -0.1700

Data Index: 1741041 (Open Web Text)

Max Activating Token Index: 751

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 12.0726. Min Range: -12.0726

Max Act: 11.0101. Min Act: -0.1700

Data Index: 484068 (Open Web Text)

Max Activating Token Index: 237

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 12.0726. Min Range: -12.0726

Max Act: 10.9476. Min Act: -0.1700

Data Index: 1225831 (Open Web Text)

Max Activating Token Index: 58

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 12.0726. Min Range: -12.0726

Max Act: 10.9476. Min Act: -0.1700

Data Index: 2374802 (Open Web Text)

Max Activating Token Index: 632

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 12.0726. Min Range: -12.0726

Max Act: 10.8851. Min Act: -0.1700

Data Index: 511802 (Open Web Text)

Max Activating Token Index: 219

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 12.0726. Min Range: -12.0726

Max Act: 10.8851. Min Act: -0.1700

Data Index: 6425340 (Open Web Text)

Max Activating Token Index: 171

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 12.0726. Min Range: -12.0726

Max Act: 10.8851. Min Act: -0.1700

Data Index: 3232825 (Open Web Text)

Max Activating Token Index: 619

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 12.0726. Min Range: -12.0726

Max Act: 10.8851. Min Act: -0.1700

Data Index: 8064122 (Open Web Text)

Max Activating Token Index: 335

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 12.0726. Min Range: -12.0726

Max Act: 10.8226. Min Act: -0.1700

Data Index: 903193 (Open Web Text)

Max Activating Token Index: 101

Click toggle to see full text

Truncated

Full Text #19