< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 806 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: 4.8959. Min Range: -4.8959

Max Act: 4.8959. Min Act: -0.1700

Data Index: 3661730 (Open Web Text)

Max Activating Token Index: 730

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 4.8959. Min Range: -4.8959

Max Act: 4.8813. Min Act: -0.1700

Data Index: 3896377 (Open Web Text)

Max Activating Token Index: 131

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 4.8959. Min Range: -4.8959

Max Act: 4.8721. Min Act: -0.1700

Data Index: 1143544 (Open Web Text)

Max Activating Token Index: 95

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 4.8959. Min Range: -4.8959

Max Act: 4.7874. Min Act: -0.1700

Data Index: 3755873 (Open Web Text)

Max Activating Token Index: 162

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 4.8959. Min Range: -4.8959

Max Act: 4.7471. Min Act: -0.1700

Data Index: 5510590 (Open Web Text)

Max Activating Token Index: 109

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 4.8959. Min Range: -4.8959

Max Act: 4.7386. Min Act: -0.1700

Data Index: 5892316 (Open Web Text)

Max Activating Token Index: 366

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 4.8959. Min Range: -4.8959

Max Act: 4.7200. Min Act: -0.1700

Data Index: 2531276 (Open Web Text)

Max Activating Token Index: 532

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 4.8959. Min Range: -4.8959

Max Act: 4.6801. Min Act: -0.1700

Data Index: 8077028 (Open Web Text)

Max Activating Token Index: 36

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 4.8959. Min Range: -4.8959

Max Act: 4.7143. Min Act: -0.1700

Data Index: 3404618 (Open Web Text)

Max Activating Token Index: 510

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 4.8959. Min Range: -4.8959

Max Act: 4.6932. Min Act: -0.1700

Data Index: 571899 (Open Web Text)

Max Activating Token Index: 146

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 4.8959. Min Range: -4.8959

Max Act: 4.6924. Min Act: -0.1700

Data Index: 1973157 (Open Web Text)

Max Activating Token Index: 431

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 4.8959. Min Range: -4.8959

Max Act: 4.6649. Min Act: -0.1700

Data Index: 4815411 (Open Web Text)

Max Activating Token Index: 996

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 4.8959. Min Range: -4.8959

Max Act: 4.6546. Min Act: -0.1700

Data Index: 8596263 (Open Web Text)

Max Activating Token Index: 522

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 4.8959. Min Range: -4.8959

Max Act: 4.6688. Min Act: -0.1700

Data Index: 2308989 (Open Web Text)

Max Activating Token Index: 571

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 4.8959. Min Range: -4.8959

Max Act: 4.6089. Min Act: -0.1700

Data Index: 4903393 (Open Web Text)

Max Activating Token Index: 992

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 4.8959. Min Range: -4.8959

Max Act: 4.6312. Min Act: -0.1700

Data Index: 1840654 (Open Web Text)

Max Activating Token Index: 465

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 4.8959. Min Range: -4.8959

Max Act: 4.6257. Min Act: -0.1700

Data Index: 4348879 (Open Web Text)

Max Activating Token Index: 817

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 4.8959. Min Range: -4.8959

Max Act: 4.6321. Min Act: -0.1700

Data Index: 6972651 (Open Web Text)

Max Activating Token Index: 959

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 4.8959. Min Range: -4.8959

Max Act: 4.6453. Min Act: -0.1700

Data Index: 5554734 (Open Web Text)

Max Activating Token Index: 988

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 4.8959. Min Range: -4.8959

Max Act: 4.5747. Min Act: -0.1700

Data Index: 669452 (Open Web Text)

Max Activating Token Index: 901

Click toggle to see full text

Truncated

Full Text #19