< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 6393 in Layer 47

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 7.4808. Min Range: -7.4808

Max Act: 7.4808. Min Act: -0.1700

Data Index: 3727933 (Open Web Text)

Max Activating Token Index: 315

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 7.4808. Min Range: -7.4808

Max Act: 7.3245. Min Act: -0.1700

Data Index: 5612656 (Open Web Text)

Max Activating Token Index: 205

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 7.4808. Min Range: -7.4808

Max Act: 7.2308. Min Act: -0.1700

Data Index: 7679719 (Open Web Text)

Max Activating Token Index: 595

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 7.4808. Min Range: -7.4808

Max Act: 7.1683. Min Act: -0.1700

Data Index: 766363 (Open Web Text)

Max Activating Token Index: 840

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 7.4808. Min Range: -7.4808

Max Act: 7.1683. Min Act: -0.1700

Data Index: 3804011 (Open Web Text)

Max Activating Token Index: 393

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 7.4808. Min Range: -7.4808

Max Act: 7.1370. Min Act: -0.1700

Data Index: 326183 (Open Web Text)

Max Activating Token Index: 505

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 7.4808. Min Range: -7.4808

Max Act: 7.1058. Min Act: -0.1700

Data Index: 3041531 (Open Web Text)

Max Activating Token Index: 1003

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 7.4808. Min Range: -7.4808

Max Act: 7.0745. Min Act: -0.1700

Data Index: 8675134 (Open Web Text)

Max Activating Token Index: 735

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 7.4808. Min Range: -7.4808

Max Act: 7.1058. Min Act: -0.1700

Data Index: 2456163 (Open Web Text)

Max Activating Token Index: 206

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 7.4808. Min Range: -7.4808

Max Act: 7.0745. Min Act: -0.1700

Data Index: 2054521 (Open Web Text)

Max Activating Token Index: 349

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 7.4808. Min Range: -7.4808

Max Act: 7.0433. Min Act: -0.1700

Data Index: 3334661 (Open Web Text)

Max Activating Token Index: 898

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 7.4808. Min Range: -7.4808

Max Act: 6.9808. Min Act: -0.1700

Data Index: 4566885 (Open Web Text)

Max Activating Token Index: 817

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 7.4808. Min Range: -7.4808

Max Act: 7.0120. Min Act: -0.1700

Data Index: 3309692 (Open Web Text)

Max Activating Token Index: 374

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 7.4808. Min Range: -7.4808

Max Act: 7.0120. Min Act: -0.1700

Data Index: 1821571 (Open Web Text)

Max Activating Token Index: 423

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 7.4808. Min Range: -7.4808

Max Act: 6.9808. Min Act: -0.1700

Data Index: 3071732 (Open Web Text)

Max Activating Token Index: 223

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 7.4808. Min Range: -7.4808

Max Act: 6.9808. Min Act: -0.1700

Data Index: 6742622 (Open Web Text)

Max Activating Token Index: 384

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 7.4808. Min Range: -7.4808

Max Act: 6.9495. Min Act: -0.1700

Data Index: 2097312 (Open Web Text)

Max Activating Token Index: 294

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 7.4808. Min Range: -7.4808

Max Act: 6.9495. Min Act: -0.1700

Data Index: 2219323 (Open Web Text)

Max Activating Token Index: 823

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 7.4808. Min Range: -7.4808

Max Act: 6.9495. Min Act: -0.1700

Data Index: 3388630 (Open Web Text)

Max Activating Token Index: 664

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 7.4808. Min Range: -7.4808

Max Act: 6.9495. Min Act: -0.1700

Data Index: 6875949 (Open Web Text)

Max Activating Token Index: 29

Click toggle to see full text

Truncated

Full Text #19