< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 762 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: 4.4696. Min Range: -4.4696

Max Act: 4.4696. Min Act: -0.1700

Data Index: 7541907 (Open Web Text)

Max Activating Token Index: 992

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 4.4696. Min Range: -4.4696

Max Act: 4.4537. Min Act: -0.1700

Data Index: 4091492 (Open Web Text)

Max Activating Token Index: 723

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 4.4696. Min Range: -4.4696

Max Act: 4.3861. Min Act: -0.1700

Data Index: 6069911 (Open Web Text)

Max Activating Token Index: 501

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 4.4696. Min Range: -4.4696

Max Act: 4.3840. Min Act: -0.1700

Data Index: 383360 (Open Web Text)

Max Activating Token Index: 300

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 4.4696. Min Range: -4.4696

Max Act: 4.4049. Min Act: -0.1700

Data Index: 3714328 (Open Web Text)

Max Activating Token Index: 449

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 4.4696. Min Range: -4.4696

Max Act: 4.3883. Min Act: -0.1700

Data Index: 5160979 (Open Web Text)

Max Activating Token Index: 196

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 4.4696. Min Range: -4.4696

Max Act: 4.4039. Min Act: -0.1700

Data Index: 1930684 (Open Web Text)

Max Activating Token Index: 741

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 4.4696. Min Range: -4.4696

Max Act: 4.3622. Min Act: -0.1700

Data Index: 1877394 (Open Web Text)

Max Activating Token Index: 189

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 4.4696. Min Range: -4.4696

Max Act: 4.3653. Min Act: -0.1700

Data Index: 7625925 (Open Web Text)

Max Activating Token Index: 460

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 4.4696. Min Range: -4.4696

Max Act: 4.3522. Min Act: -0.1700

Data Index: 3595543 (Open Web Text)

Max Activating Token Index: 329

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 4.4696. Min Range: -4.4696

Max Act: 4.3337. Min Act: -0.1700

Data Index: 5970414 (Open Web Text)

Max Activating Token Index: 392

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 4.4696. Min Range: -4.4696

Max Act: 4.3309. Min Act: -0.1700

Data Index: 1042878 (Open Web Text)

Max Activating Token Index: 815

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 4.4696. Min Range: -4.4696

Max Act: 4.3464. Min Act: -0.1700

Data Index: 368608 (Open Web Text)

Max Activating Token Index: 59

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 4.4696. Min Range: -4.4696

Max Act: 4.3494. Min Act: -0.1700

Data Index: 2683372 (Open Web Text)

Max Activating Token Index: 948

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 4.4696. Min Range: -4.4696

Max Act: 4.3531. Min Act: -0.1700

Data Index: 3491939 (Open Web Text)

Max Activating Token Index: 351

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 4.4696. Min Range: -4.4696

Max Act: 4.3290. Min Act: -0.1700

Data Index: 7147533 (Open Web Text)

Max Activating Token Index: 744

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 4.4696. Min Range: -4.4696

Max Act: 4.3267. Min Act: -0.1700

Data Index: 5188023 (Open Web Text)

Max Activating Token Index: 388

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 4.4696. Min Range: -4.4696

Max Act: 4.3209. Min Act: -0.1700

Data Index: 5164251 (Open Web Text)

Max Activating Token Index: 368

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 4.4696. Min Range: -4.4696

Max Act: 4.3097. Min Act: -0.1700

Data Index: 6836962 (Open Web Text)

Max Activating Token Index: 565

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 4.4696. Min Range: -4.4696

Max Act: 4.3455. Min Act: -0.1700

Data Index: 468084 (Open Web Text)

Max Activating Token Index: 612

Click toggle to see full text

Truncated

Full Text #19