< Prev | Home | Model | Random | Next >

Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 447 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8568. Min Range: -2.8568

Max Act: 2.8568. Min Act: -0.1700

Data Index: 5889102 (Open Web Text)

Max Activating Token Index: 809

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 2.8568. Min Range: -2.8568

Max Act: 2.8303. Min Act: -0.1700

Data Index: 3094749 (Open Web Text)

Max Activating Token Index: 944

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 2.8568. Min Range: -2.8568

Max Act: 2.7893. Min Act: -0.1700

Data Index: 4849910 (Open Web Text)

Max Activating Token Index: 602

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 2.8568. Min Range: -2.8568

Max Act: 2.8055. Min Act: -0.1700

Data Index: 6918852 (Open Web Text)

Max Activating Token Index: 233

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 2.8568. Min Range: -2.8568

Max Act: 2.8223. Min Act: -0.1700

Data Index: 7274966 (Open Web Text)

Max Activating Token Index: 771

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 2.8568. Min Range: -2.8568

Max Act: 2.7958. Min Act: -0.1700

Data Index: 713262 (Open Web Text)

Max Activating Token Index: 652

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 2.8568. Min Range: -2.8568

Max Act: 2.8002. Min Act: -0.1700

Data Index: 1733680 (Open Web Text)

Max Activating Token Index: 315

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 2.8568. Min Range: -2.8568

Max Act: 2.8015. Min Act: -0.1700

Data Index: 2566795 (Open Web Text)

Max Activating Token Index: 599

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 2.8568. Min Range: -2.8568

Max Act: 2.7809. Min Act: -0.1700

Data Index: 4558652 (Open Web Text)

Max Activating Token Index: 140

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 2.8568. Min Range: -2.8568

Max Act: 2.7748. Min Act: -0.1700

Data Index: 2381649 (Open Web Text)

Max Activating Token Index: 927

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 2.8568. Min Range: -2.8568

Max Act: 2.7736. Min Act: -0.1700

Data Index: 5295150 (Open Web Text)

Max Activating Token Index: 945

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 2.8568. Min Range: -2.8568

Max Act: 2.7644. Min Act: -0.1700

Data Index: 1014872 (Open Web Text)

Max Activating Token Index: 373

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 2.8568. Min Range: -2.8568

Max Act: 2.7669. Min Act: -0.1700

Data Index: 5178264 (Open Web Text)

Max Activating Token Index: 974

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 2.8568. Min Range: -2.8568

Max Act: 2.7692. Min Act: -0.1700

Data Index: 33677 (Open Web Text)

Max Activating Token Index: 223

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 2.8568. Min Range: -2.8568

Max Act: 2.7546. Min Act: -0.1700

Data Index: 760318 (Open Web Text)

Max Activating Token Index: 679

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 2.8568. Min Range: -2.8568

Max Act: 2.7427. Min Act: -0.1700

Data Index: 6605936 (Open Web Text)

Max Activating Token Index: 277

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 2.8568. Min Range: -2.8568

Max Act: 2.7735. Min Act: -0.1700

Data Index: 2330148 (Open Web Text)

Max Activating Token Index: 924

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 2.8568. Min Range: -2.8568

Max Act: 2.7425. Min Act: -0.1700

Data Index: 6883655 (Open Web Text)

Max Activating Token Index: 734

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 2.8568. Min Range: -2.8568

Max Act: 2.7173. Min Act: -0.1700

Data Index: 876612 (Open Web Text)

Max Activating Token Index: 439

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 2.8568. Min Range: -2.8568

Max Act: 2.7384. Min Act: -0.1700

Data Index: 1090814 (Open Web Text)

Max Activating Token Index: 767

Click toggle to see full text

Truncated

Full Text #19