< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 22 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 4.6192. Min Range: -4.6192

Max Act: 4.6192. Min Act: -0.1700

Data Index: 6371015 (The Pile)

Max Activating Token Index: 709

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 4.6192. Min Range: -4.6192

Max Act: 4.6192. Min Act: -0.1700

Data Index: 6988508 (The Pile)

Max Activating Token Index: 901

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 4.6192. Min Range: -4.6192

Max Act: 4.6192. Min Act: -0.1700

Data Index: 9071368 (The Pile)

Max Activating Token Index: 123

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 4.6192. Min Range: -4.6192

Max Act: 4.6192. Min Act: -0.1700

Data Index: 6683953 (The Pile)

Max Activating Token Index: 818

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 4.6192. Min Range: -4.6192

Max Act: 4.5880. Min Act: -0.1700

Data Index: 4345794 (The Pile)

Max Activating Token Index: 280

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 4.6192. Min Range: -4.6192

Max Act: 4.5880. Min Act: -0.1700

Data Index: 7195687 (The Pile)

Max Activating Token Index: 940

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 4.6192. Min Range: -4.6192

Max Act: 4.5880. Min Act: -0.1700

Data Index: 6961657 (The Pile)

Max Activating Token Index: 615

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 4.6192. Min Range: -4.6192

Max Act: 4.5880. Min Act: -0.1700

Data Index: 3339439 (The Pile)

Max Activating Token Index: 418

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 4.6192. Min Range: -4.6192

Max Act: 4.5880. Min Act: -0.1700

Data Index: 9486256 (The Pile)

Max Activating Token Index: 811

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 4.6192. Min Range: -4.6192

Max Act: 4.5880. Min Act: -0.1700

Data Index: 9159276 (The Pile)

Max Activating Token Index: 347

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 4.6192. Min Range: -4.6192

Max Act: 4.5880. Min Act: -0.1700

Data Index: 3238544 (The Pile)

Max Activating Token Index: 931

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 4.6192. Min Range: -4.6192

Max Act: 4.5567. Min Act: -0.1700

Data Index: 1139093 (The Pile)

Max Activating Token Index: 485

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 4.6192. Min Range: -4.6192

Max Act: 4.5567. Min Act: -0.1700

Data Index: 3597198 (The Pile)

Max Activating Token Index: 855

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 4.6192. Min Range: -4.6192

Max Act: 4.5567. Min Act: -0.1700

Data Index: 1887403 (The Pile)

Max Activating Token Index: 470

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 4.6192. Min Range: -4.6192

Max Act: 4.5567. Min Act: -0.1700

Data Index: 7225110 (The Pile)

Max Activating Token Index: 593

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 4.6192. Min Range: -4.6192

Max Act: 4.5567. Min Act: -0.1700

Data Index: 7329802 (The Pile)

Max Activating Token Index: 608

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 4.6192. Min Range: -4.6192

Max Act: 4.5567. Min Act: -0.1700

Data Index: 7343111 (The Pile)

Max Activating Token Index: 548

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 4.6192. Min Range: -4.6192

Max Act: 4.5567. Min Act: -0.1700

Data Index: 8074926 (The Pile)

Max Activating Token Index: 720

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 4.6192. Min Range: -4.6192

Max Act: 4.5567. Min Act: -0.1700

Data Index: 5395312 (The Pile)

Max Activating Token Index: 929

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 4.6192. Min Range: -4.6192

Max Act: 4.5567. Min Act: -0.1700

Data Index: 5688796 (The Pile)

Max Activating Token Index: 545

Click toggle to see full text

Truncated

Full Text #19