< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 2006 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-70m')



Text #0

Max Range: 4.0642. Min Range: -4.0642

Max Act: 4.0642. Min Act: -0.1700

Data Index: 7089093 (The Pile)

Max Activating Token Index: 628

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 4.0642. Min Range: -4.0642

Max Act: 3.9079. Min Act: -0.1700

Data Index: 2971156 (The Pile)

Max Activating Token Index: 974

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 4.0642. Min Range: -4.0642

Max Act: 3.7828. Min Act: -0.1700

Data Index: 10091315 (The Pile)

Max Activating Token Index: 656

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 4.0642. Min Range: -4.0642

Max Act: 3.7828. Min Act: -0.1700

Data Index: 3793440 (The Pile)

Max Activating Token Index: 453

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 4.0642. Min Range: -4.0642

Max Act: 3.6889. Min Act: -0.1700

Data Index: 5790676 (The Pile)

Max Activating Token Index: 595

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 4.0642. Min Range: -4.0642

Max Act: 3.6576. Min Act: -0.1700

Data Index: 6876996 (The Pile)

Max Activating Token Index: 54

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 4.0642. Min Range: -4.0642

Max Act: 3.6576. Min Act: -0.1700

Data Index: 1580931 (The Pile)

Max Activating Token Index: 14

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 4.0642. Min Range: -4.0642

Max Act: 3.6576. Min Act: -0.1700

Data Index: 10528382 (The Pile)

Max Activating Token Index: 14

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 4.0642. Min Range: -4.0642

Max Act: 3.5950. Min Act: -0.1700

Data Index: 5379402 (The Pile)

Max Activating Token Index: 12

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 4.0642. Min Range: -4.0642

Max Act: 3.6263. Min Act: -0.1700

Data Index: 158225 (The Pile)

Max Activating Token Index: 442

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 4.0642. Min Range: -4.0642

Max Act: 3.6263. Min Act: -0.1700

Data Index: 203297 (The Pile)

Max Activating Token Index: 84

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 4.0642. Min Range: -4.0642

Max Act: 3.5950. Min Act: -0.1700

Data Index: 2354269 (The Pile)

Max Activating Token Index: 373

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 4.0642. Min Range: -4.0642

Max Act: 3.6263. Min Act: -0.1700

Data Index: 8858552 (The Pile)

Max Activating Token Index: 56

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 4.0642. Min Range: -4.0642

Max Act: 3.5950. Min Act: -0.1700

Data Index: 3304732 (The Pile)

Max Activating Token Index: 26

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 4.0642. Min Range: -4.0642

Max Act: 3.5950. Min Act: -0.1700

Data Index: 5925922 (The Pile)

Max Activating Token Index: 76

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 4.0642. Min Range: -4.0642

Max Act: 3.5950. Min Act: -0.1700

Data Index: 6669297 (The Pile)

Max Activating Token Index: 64

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 4.0642. Min Range: -4.0642

Max Act: 3.5950. Min Act: -0.1700

Data Index: 8230651 (The Pile)

Max Activating Token Index: 34

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 4.0642. Min Range: -4.0642

Max Act: 3.5950. Min Act: -0.1700

Data Index: 8239037 (The Pile)

Max Activating Token Index: 19

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 4.0642. Min Range: -4.0642

Max Act: 3.5950. Min Act: -0.1700

Data Index: 2136343 (The Pile)

Max Activating Token Index: 135

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 4.0642. Min Range: -4.0642

Max Act: 3.5950. Min Act: -0.1700

Data Index: 8440553 (The Pile)

Max Activating Token Index: 116

Click toggle to see full text

Truncated

Full Text #19