< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 2997 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-160m')



Text #0

Max Range: 2.7080. Min Range: -2.7080

Max Act: 2.7080. Min Act: -0.1700

Data Index: 5012968 (The Pile)

Max Activating Token Index: 695

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 2.7080. Min Range: -2.7080

Max Act: 2.6920. Min Act: -0.1700

Data Index: 5436927 (The Pile)

Max Activating Token Index: 755

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 2.7080. Min Range: -2.7080

Max Act: 2.6920. Min Act: -0.1700

Data Index: 8499460 (The Pile)

Max Activating Token Index: 808

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 2.7080. Min Range: -2.7080

Max Act: 2.6920. Min Act: -0.1700

Data Index: 4342679 (The Pile)

Max Activating Token Index: 189

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 2.7080. Min Range: -2.7080

Max Act: 2.6759. Min Act: -0.1700

Data Index: 10442691 (The Pile)

Max Activating Token Index: 847

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 2.7080. Min Range: -2.7080

Max Act: 2.6599. Min Act: -0.1700

Data Index: 7973952 (The Pile)

Max Activating Token Index: 868

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 2.7080. Min Range: -2.7080

Max Act: 2.6599. Min Act: -0.1700

Data Index: 7792042 (The Pile)

Max Activating Token Index: 720

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 2.7080. Min Range: -2.7080

Max Act: 2.6439. Min Act: -0.1700

Data Index: 6163195 (The Pile)

Max Activating Token Index: 415

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 2.7080. Min Range: -2.7080

Max Act: 2.6439. Min Act: -0.1700

Data Index: 1561600 (The Pile)

Max Activating Token Index: 658

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 2.7080. Min Range: -2.7080

Max Act: 2.6439. Min Act: -0.1700

Data Index: 3531046 (The Pile)

Max Activating Token Index: 243

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 2.7080. Min Range: -2.7080

Max Act: 2.6439. Min Act: -0.1700

Data Index: 6745928 (The Pile)

Max Activating Token Index: 887

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 2.7080. Min Range: -2.7080

Max Act: 2.6439. Min Act: -0.1700

Data Index: 899958 (The Pile)

Max Activating Token Index: 175

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 2.7080. Min Range: -2.7080

Max Act: 2.6439. Min Act: -0.1700

Data Index: 10720927 (The Pile)

Max Activating Token Index: 751

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 2.7080. Min Range: -2.7080

Max Act: 2.6278. Min Act: -0.1700

Data Index: 177089 (The Pile)

Max Activating Token Index: 942

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 2.7080. Min Range: -2.7080

Max Act: 2.6278. Min Act: -0.1700

Data Index: 7951890 (The Pile)

Max Activating Token Index: 1007

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 2.7080. Min Range: -2.7080

Max Act: 2.6278. Min Act: -0.1700

Data Index: 1151098 (The Pile)

Max Activating Token Index: 564

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 2.7080. Min Range: -2.7080

Max Act: 2.6278. Min Act: -0.1700

Data Index: 5391560 (The Pile)

Max Activating Token Index: 809

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 2.7080. Min Range: -2.7080

Max Act: 2.6278. Min Act: -0.1700

Data Index: 2557405 (The Pile)

Max Activating Token Index: 444

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 2.7080. Min Range: -2.7080

Max Act: 2.6278. Min Act: -0.1700

Data Index: 643613 (The Pile)

Max Activating Token Index: 988

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 2.7080. Min Range: -2.7080

Max Act: 2.6117. Min Act: -0.1700

Data Index: 7139503 (The Pile)

Max Activating Token Index: 818

Click toggle to see full text

Truncated

Full Text #19