< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 6396 in Layer 42

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 10.6678. Min Range: -10.6678

Max Act: 10.6678. Min Act: -0.1700

Data Index: 8162015 (Open Web Text)

Max Activating Token Index: 644

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 10.6678. Min Range: -10.6678

Max Act: 10.3553. Min Act: -0.1700

Data Index: 6958145 (Open Web Text)

Max Activating Token Index: 800

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 10.6678. Min Range: -10.6678

Max Act: 10.1678. Min Act: -0.1700

Data Index: 178782 (Open Web Text)

Max Activating Token Index: 442

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 10.6678. Min Range: -10.6678

Max Act: 9.7303. Min Act: -0.1700

Data Index: 1859107 (Open Web Text)

Max Activating Token Index: 229

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 10.6678. Min Range: -10.6678

Max Act: 9.7303. Min Act: -0.1700

Data Index: 5772402 (Open Web Text)

Max Activating Token Index: 901

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 10.6678. Min Range: -10.6678

Max Act: 9.6678. Min Act: -0.1700

Data Index: 7411723 (Open Web Text)

Max Activating Token Index: 386

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 10.6678. Min Range: -10.6678

Max Act: 9.6053. Min Act: -0.1700

Data Index: 52335 (Open Web Text)

Max Activating Token Index: 636

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 10.6678. Min Range: -10.6678

Max Act: 9.6053. Min Act: -0.1700

Data Index: 1510700 (Open Web Text)

Max Activating Token Index: 146

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 10.6678. Min Range: -10.6678

Max Act: 9.6053. Min Act: -0.1700

Data Index: 7827400 (Open Web Text)

Max Activating Token Index: 784

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 10.6678. Min Range: -10.6678

Max Act: 9.5428. Min Act: -0.1700

Data Index: 1715869 (Open Web Text)

Max Activating Token Index: 381

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 10.6678. Min Range: -10.6678

Max Act: 9.5428. Min Act: -0.1700

Data Index: 1072491 (Open Web Text)

Max Activating Token Index: 754

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 10.6678. Min Range: -10.6678

Max Act: 9.5428. Min Act: -0.1700

Data Index: 6966080 (Open Web Text)

Max Activating Token Index: 562

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 10.6678. Min Range: -10.6678

Max Act: 9.4803. Min Act: -0.1700

Data Index: 8436977 (Open Web Text)

Max Activating Token Index: 733

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 10.6678. Min Range: -10.6678

Max Act: 9.4803. Min Act: -0.1700

Data Index: 1366581 (Open Web Text)

Max Activating Token Index: 206

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 10.6678. Min Range: -10.6678

Max Act: 9.4803. Min Act: -0.1700

Data Index: 5338856 (Open Web Text)

Max Activating Token Index: 806

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 10.6678. Min Range: -10.6678

Max Act: 9.5428. Min Act: -0.1700

Data Index: 7421052 (Open Web Text)

Max Activating Token Index: 593

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 10.6678. Min Range: -10.6678

Max Act: 9.4803. Min Act: -0.1700

Data Index: 7113102 (Open Web Text)

Max Activating Token Index: 446

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 10.6678. Min Range: -10.6678

Max Act: 9.4178. Min Act: -0.1700

Data Index: 2350166 (Open Web Text)

Max Activating Token Index: 825

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 10.6678. Min Range: -10.6678

Max Act: 9.4178. Min Act: -0.1700

Data Index: 1679491 (Open Web Text)

Max Activating Token Index: 93

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 10.6678. Min Range: -10.6678

Max Act: 9.4803. Min Act: -0.1700

Data Index: 5754520 (Open Web Text)

Max Activating Token Index: 888

Click toggle to see full text

Truncated

Full Text #19