< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 6395 in Layer 33

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 10.1041. Min Range: -10.1041

Max Act: 10.1041. Min Act: -0.1700

Data Index: 7119191 (Open Web Text)

Max Activating Token Index: 583

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 10.1041. Min Range: -10.1041

Max Act: 9.9166. Min Act: -0.1700

Data Index: 3615338 (Open Web Text)

Max Activating Token Index: 612

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 10.1041. Min Range: -10.1041

Max Act: 9.9166. Min Act: -0.1700

Data Index: 4229223 (Open Web Text)

Max Activating Token Index: 285

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 10.1041. Min Range: -10.1041

Max Act: 9.7916. Min Act: -0.1700

Data Index: 6330249 (Open Web Text)

Max Activating Token Index: 624

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 10.1041. Min Range: -10.1041

Max Act: 9.7916. Min Act: -0.1700

Data Index: 1338526 (Open Web Text)

Max Activating Token Index: 351

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 10.1041. Min Range: -10.1041

Max Act: 9.6041. Min Act: -0.1700

Data Index: 5073968 (Open Web Text)

Max Activating Token Index: 433

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 10.1041. Min Range: -10.1041

Max Act: 9.5416. Min Act: -0.1700

Data Index: 254439 (Open Web Text)

Max Activating Token Index: 603

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 10.1041. Min Range: -10.1041

Max Act: 9.5416. Min Act: -0.1700

Data Index: 135129 (Open Web Text)

Max Activating Token Index: 277

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 10.1041. Min Range: -10.1041

Max Act: 9.5416. Min Act: -0.1700

Data Index: 1699759 (Open Web Text)

Max Activating Token Index: 330

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 10.1041. Min Range: -10.1041

Max Act: 9.5416. Min Act: -0.1700

Data Index: 7457942 (Open Web Text)

Max Activating Token Index: 787

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 10.1041. Min Range: -10.1041

Max Act: 9.4791. Min Act: -0.1700

Data Index: 5753005 (Open Web Text)

Max Activating Token Index: 1004

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 10.1041. Min Range: -10.1041

Max Act: 9.4166. Min Act: -0.1700

Data Index: 7609790 (Open Web Text)

Max Activating Token Index: 52

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 10.1041. Min Range: -10.1041

Max Act: 9.4791. Min Act: -0.1700

Data Index: 7962193 (Open Web Text)

Max Activating Token Index: 12

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 10.1041. Min Range: -10.1041

Max Act: 9.4791. Min Act: -0.1700

Data Index: 3203009 (Open Web Text)

Max Activating Token Index: 119

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 10.1041. Min Range: -10.1041

Max Act: 9.5416. Min Act: -0.1700

Data Index: 4054499 (Open Web Text)

Max Activating Token Index: 889

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 10.1041. Min Range: -10.1041

Max Act: 9.4166. Min Act: -0.1700

Data Index: 1460300 (Open Web Text)

Max Activating Token Index: 190

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 10.1041. Min Range: -10.1041

Max Act: 9.4166. Min Act: -0.1700

Data Index: 4833555 (Open Web Text)

Max Activating Token Index: 42

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 10.1041. Min Range: -10.1041

Max Act: 9.4166. Min Act: -0.1700

Data Index: 3723370 (Open Web Text)

Max Activating Token Index: 35

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 10.1041. Min Range: -10.1041

Max Act: 9.3541. Min Act: -0.1700

Data Index: 7481929 (Open Web Text)

Max Activating Token Index: 133

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 10.1041. Min Range: -10.1041

Max Act: 9.3541. Min Act: -0.1700

Data Index: 7587626 (Open Web Text)

Max Activating Token Index: 938

Click toggle to see full text

Truncated

Full Text #19