< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 40 in Layer 43

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 10.0570. Min Range: -10.0570

Max Act: 10.0570. Min Act: -0.1700

Data Index: 7152889 (Open Web Text)

Max Activating Token Index: 897

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 10.0570. Min Range: -10.0570

Max Act: 9.8695. Min Act: -0.1700

Data Index: 7607802 (Open Web Text)

Max Activating Token Index: 890

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 10.0570. Min Range: -10.0570

Max Act: 9.6820. Min Act: -0.1700

Data Index: 6942867 (Open Web Text)

Max Activating Token Index: 895

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 10.0570. Min Range: -10.0570

Max Act: 9.5570. Min Act: -0.1700

Data Index: 8362482 (Open Web Text)

Max Activating Token Index: 477

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 10.0570. Min Range: -10.0570

Max Act: 9.4945. Min Act: -0.1700

Data Index: 5248577 (Open Web Text)

Max Activating Token Index: 690

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 10.0570. Min Range: -10.0570

Max Act: 9.4945. Min Act: -0.1700

Data Index: 125074 (Open Web Text)

Max Activating Token Index: 559

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 10.0570. Min Range: -10.0570

Max Act: 9.3070. Min Act: -0.1700

Data Index: 3087728 (Open Web Text)

Max Activating Token Index: 614

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 10.0570. Min Range: -10.0570

Max Act: 9.3070. Min Act: -0.1700

Data Index: 2115494 (Open Web Text)

Max Activating Token Index: 263

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 10.0570. Min Range: -10.0570

Max Act: 9.3070. Min Act: -0.1700

Data Index: 8116955 (Open Web Text)

Max Activating Token Index: 419

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 10.0570. Min Range: -10.0570

Max Act: 9.2445. Min Act: -0.1700

Data Index: 6371406 (Open Web Text)

Max Activating Token Index: 673

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 10.0570. Min Range: -10.0570

Max Act: 9.2445. Min Act: -0.1700

Data Index: 538542 (Open Web Text)

Max Activating Token Index: 764

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 10.0570. Min Range: -10.0570

Max Act: 9.2445. Min Act: -0.1700

Data Index: 7897012 (Open Web Text)

Max Activating Token Index: 442

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 10.0570. Min Range: -10.0570

Max Act: 9.2445. Min Act: -0.1700

Data Index: 8487694 (Open Web Text)

Max Activating Token Index: 606

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 10.0570. Min Range: -10.0570

Max Act: 9.1820. Min Act: -0.1700

Data Index: 8233487 (Open Web Text)

Max Activating Token Index: 229

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 10.0570. Min Range: -10.0570

Max Act: 9.1195. Min Act: -0.1700

Data Index: 2110095 (Open Web Text)

Max Activating Token Index: 314

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 10.0570. Min Range: -10.0570

Max Act: 9.1195. Min Act: -0.1700

Data Index: 6760399 (Open Web Text)

Max Activating Token Index: 557

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 10.0570. Min Range: -10.0570

Max Act: 8.9945. Min Act: -0.1700

Data Index: 3589421 (Open Web Text)

Max Activating Token Index: 489

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 10.0570. Min Range: -10.0570

Max Act: 9.0570. Min Act: -0.1700

Data Index: 916572 (Open Web Text)

Max Activating Token Index: 759

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 10.0570. Min Range: -10.0570

Max Act: 9.0570. Min Act: -0.1700

Data Index: 3561156 (Open Web Text)

Max Activating Token Index: 326

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 10.0570. Min Range: -10.0570

Max Act: 9.0570. Min Act: -0.1700

Data Index: 5048393 (Open Web Text)

Max Activating Token Index: 190

Click toggle to see full text

Truncated

Full Text #19