< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 6380 in Layer 38

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 14.9130. Min Range: -14.9130

Max Act: 14.9130. Min Act: -0.1700

Data Index: 4786805 (Open Web Text)

Max Activating Token Index: 338

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 14.9130. Min Range: -14.9130

Max Act: 14.9130. Min Act: -0.1700

Data Index: 6180724 (Open Web Text)

Max Activating Token Index: 288

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 14.9130. Min Range: -14.9130

Max Act: 14.6630. Min Act: -0.1700

Data Index: 3226479 (Open Web Text)

Max Activating Token Index: 424

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 14.9130. Min Range: -14.9130

Max Act: 14.6630. Min Act: -0.1700

Data Index: 3160827 (Open Web Text)

Max Activating Token Index: 654

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 14.9130. Min Range: -14.9130

Max Act: 14.6005. Min Act: -0.1700

Data Index: 1291689 (Open Web Text)

Max Activating Token Index: 864

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 14.9130. Min Range: -14.9130

Max Act: 14.5380. Min Act: -0.1700

Data Index: 8581982 (Open Web Text)

Max Activating Token Index: 272

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 14.9130. Min Range: -14.9130

Max Act: 14.5380. Min Act: -0.1700

Data Index: 6247164 (Open Web Text)

Max Activating Token Index: 239

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 14.9130. Min Range: -14.9130

Max Act: 14.4755. Min Act: -0.1700

Data Index: 5967427 (Open Web Text)

Max Activating Token Index: 552

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 14.9130. Min Range: -14.9130

Max Act: 14.3505. Min Act: -0.1700

Data Index: 6608835 (Open Web Text)

Max Activating Token Index: 659

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 14.9130. Min Range: -14.9130

Max Act: 14.1630. Min Act: -0.1700

Data Index: 2549374 (Open Web Text)

Max Activating Token Index: 524

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 14.9130. Min Range: -14.9130

Max Act: 14.1630. Min Act: -0.1700

Data Index: 1053246 (Open Web Text)

Max Activating Token Index: 431

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 14.9130. Min Range: -14.9130

Max Act: 14.2255. Min Act: -0.1700

Data Index: 5028094 (Open Web Text)

Max Activating Token Index: 782

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 14.9130. Min Range: -14.9130

Max Act: 14.1005. Min Act: -0.1700

Data Index: 8664056 (Open Web Text)

Max Activating Token Index: 341

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 14.9130. Min Range: -14.9130

Max Act: 13.9755. Min Act: -0.1700

Data Index: 8760748 (Open Web Text)

Max Activating Token Index: 534

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 14.9130. Min Range: -14.9130

Max Act: 13.9755. Min Act: -0.1700

Data Index: 4589544 (Open Web Text)

Max Activating Token Index: 977

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 14.9130. Min Range: -14.9130

Max Act: 13.9755. Min Act: -0.1700

Data Index: 1043986 (Open Web Text)

Max Activating Token Index: 330

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 14.9130. Min Range: -14.9130

Max Act: 13.9755. Min Act: -0.1700

Data Index: 3094938 (Open Web Text)

Max Activating Token Index: 93

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 14.9130. Min Range: -14.9130

Max Act: 13.9130. Min Act: -0.1700

Data Index: 5470598 (Open Web Text)

Max Activating Token Index: 459

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 14.9130. Min Range: -14.9130

Max Act: 13.9130. Min Act: -0.1700

Data Index: 1834284 (Open Web Text)

Max Activating Token Index: 65

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 14.9130. Min Range: -14.9130

Max Act: 13.8505. Min Act: -0.1700

Data Index: 6016635 (Open Web Text)

Max Activating Token Index: 363

Click toggle to see full text

Truncated

Full Text #19