< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 4088 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-350m')



Text #0

Max Range: 2.9763. Min Range: -2.9763

Max Act: 2.9763. Min Act: -0.1700

Data Index: 10620907 (The Pile)

Max Activating Token Index: 688

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 2.9763. Min Range: -2.9763

Max Act: 2.9447. Min Act: -0.1700

Data Index: 1520312 (The Pile)

Max Activating Token Index: 813

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 2.9763. Min Range: -2.9763

Max Act: 2.9447. Min Act: -0.1700

Data Index: 6607541 (The Pile)

Max Activating Token Index: 928

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 2.9763. Min Range: -2.9763

Max Act: 2.9447. Min Act: -0.1700

Data Index: 5927502 (The Pile)

Max Activating Token Index: 56

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 2.9763. Min Range: -2.9763

Max Act: 2.9447. Min Act: -0.1700

Data Index: 5905974 (The Pile)

Max Activating Token Index: 759

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 2.9763. Min Range: -2.9763

Max Act: 2.9447. Min Act: -0.1700

Data Index: 598338 (The Pile)

Max Activating Token Index: 413

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 2.9763. Min Range: -2.9763

Max Act: 2.9130. Min Act: -0.1700

Data Index: 70177 (The Pile)

Max Activating Token Index: 924

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 2.9763. Min Range: -2.9763

Max Act: 2.8971. Min Act: -0.1700

Data Index: 3204891 (The Pile)

Max Activating Token Index: 946

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 2.9763. Min Range: -2.9763

Max Act: 2.8971. Min Act: -0.1700

Data Index: 8694472 (The Pile)

Max Activating Token Index: 13

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 2.9763. Min Range: -2.9763

Max Act: 2.8813. Min Act: -0.1700

Data Index: 4580878 (The Pile)

Max Activating Token Index: 387

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 2.9763. Min Range: -2.9763

Max Act: 2.8813. Min Act: -0.1700

Data Index: 10547691 (The Pile)

Max Activating Token Index: 223

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 2.9763. Min Range: -2.9763

Max Act: 2.8813. Min Act: -0.1700

Data Index: 1906974 (The Pile)

Max Activating Token Index: 380

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 2.9763. Min Range: -2.9763

Max Act: 2.8813. Min Act: -0.1700

Data Index: 135389 (The Pile)

Max Activating Token Index: 472

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 2.9763. Min Range: -2.9763

Max Act: 2.8654. Min Act: -0.1700

Data Index: 6071768 (The Pile)

Max Activating Token Index: 598

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 2.9763. Min Range: -2.9763

Max Act: 2.8654. Min Act: -0.1700

Data Index: 8576555 (The Pile)

Max Activating Token Index: 741

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 2.9763. Min Range: -2.9763

Max Act: 2.8654. Min Act: -0.1700

Data Index: 1090599 (The Pile)

Max Activating Token Index: 902

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 2.9763. Min Range: -2.9763

Max Act: 2.8495. Min Act: -0.1700

Data Index: 5767868 (The Pile)

Max Activating Token Index: 946

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 2.9763. Min Range: -2.9763

Max Act: 2.8495. Min Act: -0.1700

Data Index: 8352856 (The Pile)

Max Activating Token Index: 240

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 2.9763. Min Range: -2.9763

Max Act: 2.8495. Min Act: -0.1700

Data Index: 7792127 (The Pile)

Max Activating Token Index: 126

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 2.9763. Min Range: -2.9763

Max Act: 2.8495. Min Act: -0.1700

Data Index: 2071077 (The Pile)

Max Activating Token Index: 271

Click toggle to see full text

Truncated

Full Text #19