< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 23 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: 2.6567. Min Range: -2.6567

Max Act: 2.6567. Min Act: -0.1700

Data Index: 7782011 (The Pile)

Max Activating Token Index: 332

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 2.6567. Min Range: -2.6567

Max Act: 2.6407. Min Act: -0.1700

Data Index: 8670087 (The Pile)

Max Activating Token Index: 999

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 2.6567. Min Range: -2.6567

Max Act: 2.6086. Min Act: -0.1700

Data Index: 9391953 (The Pile)

Max Activating Token Index: 648

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 2.6567. Min Range: -2.6567

Max Act: 2.6086. Min Act: -0.1700

Data Index: 7110925 (The Pile)

Max Activating Token Index: 108

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 2.6567. Min Range: -2.6567

Max Act: 2.5925. Min Act: -0.1700

Data Index: 3390109 (The Pile)

Max Activating Token Index: 84

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 2.6567. Min Range: -2.6567

Max Act: 2.5764. Min Act: -0.1700

Data Index: 1354273 (The Pile)

Max Activating Token Index: 805

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 2.6567. Min Range: -2.6567

Max Act: 2.5602. Min Act: -0.1700

Data Index: 2674029 (The Pile)

Max Activating Token Index: 690

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 2.6567. Min Range: -2.6567

Max Act: 2.5441. Min Act: -0.1700

Data Index: 6223234 (The Pile)

Max Activating Token Index: 663

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 2.6567. Min Range: -2.6567

Max Act: 2.5441. Min Act: -0.1700

Data Index: 2737591 (The Pile)

Max Activating Token Index: 80

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 2.6567. Min Range: -2.6567

Max Act: 2.5279. Min Act: -0.1700

Data Index: 778017 (The Pile)

Max Activating Token Index: 153

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 2.6567. Min Range: -2.6567

Max Act: 2.5279. Min Act: -0.1700

Data Index: 9497677 (The Pile)

Max Activating Token Index: 606

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 2.6567. Min Range: -2.6567

Max Act: 2.5279. Min Act: -0.1700

Data Index: 522698 (The Pile)

Max Activating Token Index: 731

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 2.6567. Min Range: -2.6567

Max Act: 2.5279. Min Act: -0.1700

Data Index: 4684664 (The Pile)

Max Activating Token Index: 465

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 2.6567. Min Range: -2.6567

Max Act: 2.5279. Min Act: -0.1700

Data Index: 6487656 (The Pile)

Max Activating Token Index: 187

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 2.6567. Min Range: -2.6567

Max Act: 2.5118. Min Act: -0.1700

Data Index: 5257551 (The Pile)

Max Activating Token Index: 770

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 2.6567. Min Range: -2.6567

Max Act: 2.5118. Min Act: -0.1700

Data Index: 6686278 (The Pile)

Max Activating Token Index: 100

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 2.6567. Min Range: -2.6567

Max Act: 2.5118. Min Act: -0.1700

Data Index: 2305372 (The Pile)

Max Activating Token Index: 1011

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 2.6567. Min Range: -2.6567

Max Act: 2.5118. Min Act: -0.1700

Data Index: 98257 (The Pile)

Max Activating Token Index: 976

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 2.6567. Min Range: -2.6567

Max Act: 2.5118. Min Act: -0.1700

Data Index: 4070439 (The Pile)

Max Activating Token Index: 261

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 2.6567. Min Range: -2.6567

Max Act: 2.5118. Min Act: -0.1700

Data Index: 1843472 (The Pile)

Max Activating Token Index: 169

Click toggle to see full text

Truncated

Full Text #19