< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 56 in Layer 26

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 6.5660. Min Range: -6.5660

Max Act: 6.5660. Min Act: -0.1700

Data Index: 7220643 (Open Web Text)

Max Activating Token Index: 839

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 6.5660. Min Range: -6.5660

Max Act: 6.2535. Min Act: -0.1700

Data Index: 2164897 (Open Web Text)

Max Activating Token Index: 968

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 6.5660. Min Range: -6.5660

Max Act: 6.2535. Min Act: -0.1700

Data Index: 1204880 (Open Web Text)

Max Activating Token Index: 960

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 6.5660. Min Range: -6.5660

Max Act: 6.1910. Min Act: -0.1700

Data Index: 6441629 (Open Web Text)

Max Activating Token Index: 542

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 6.5660. Min Range: -6.5660

Max Act: 6.1597. Min Act: -0.1700

Data Index: 733757 (Open Web Text)

Max Activating Token Index: 684

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 6.5660. Min Range: -6.5660

Max Act: 6.1285. Min Act: -0.1700

Data Index: 3090042 (Open Web Text)

Max Activating Token Index: 298

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 6.5660. Min Range: -6.5660

Max Act: 6.1285. Min Act: -0.1700

Data Index: 2341781 (Open Web Text)

Max Activating Token Index: 78

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 6.5660. Min Range: -6.5660

Max Act: 6.0660. Min Act: -0.1700

Data Index: 8490303 (Open Web Text)

Max Activating Token Index: 614

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 6.5660. Min Range: -6.5660

Max Act: 6.0347. Min Act: -0.1700

Data Index: 3509049 (Open Web Text)

Max Activating Token Index: 243

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 6.5660. Min Range: -6.5660

Max Act: 6.0035. Min Act: -0.1700

Data Index: 3589264 (Open Web Text)

Max Activating Token Index: 262

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 6.5660. Min Range: -6.5660

Max Act: 6.0347. Min Act: -0.1700

Data Index: 2668737 (Open Web Text)

Max Activating Token Index: 729

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 6.5660. Min Range: -6.5660

Max Act: 6.0035. Min Act: -0.1700

Data Index: 2004847 (Open Web Text)

Max Activating Token Index: 321

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 6.5660. Min Range: -6.5660

Max Act: 6.0035. Min Act: -0.1700

Data Index: 7334286 (Open Web Text)

Max Activating Token Index: 552

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 6.5660. Min Range: -6.5660

Max Act: 6.0035. Min Act: -0.1700

Data Index: 6540720 (Open Web Text)

Max Activating Token Index: 64

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 6.5660. Min Range: -6.5660

Max Act: 6.0035. Min Act: -0.1700

Data Index: 820758 (Open Web Text)

Max Activating Token Index: 925

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 6.5660. Min Range: -6.5660

Max Act: 5.9722. Min Act: -0.1700

Data Index: 6434305 (Open Web Text)

Max Activating Token Index: 767

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 6.5660. Min Range: -6.5660

Max Act: 6.0035. Min Act: -0.1700

Data Index: 5925557 (Open Web Text)

Max Activating Token Index: 420

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 6.5660. Min Range: -6.5660

Max Act: 5.9722. Min Act: -0.1700

Data Index: 8118972 (Open Web Text)

Max Activating Token Index: 672

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 6.5660. Min Range: -6.5660

Max Act: 5.9410. Min Act: -0.1700

Data Index: 4853876 (Open Web Text)

Max Activating Token Index: 780

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 6.5660. Min Range: -6.5660

Max Act: 5.9097. Min Act: -0.1700

Data Index: 946721 (Open Web Text)

Max Activating Token Index: 423

Click toggle to see full text

Truncated

Full Text #19