< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 2023 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 1.9792. Min Range: -1.9792

Max Act: 1.9792. Min Act: -0.1700

Data Index: 341 (The Pile)

Max Activating Token Index: 125

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 1.9792. Min Range: -1.9792

Max Act: 1.9792. Min Act: -0.1700

Data Index: 422 (The Pile)

Max Activating Token Index: 660

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 1.9792. Min Range: -1.9792

Max Act: 1.9792. Min Act: -0.1700

Data Index: 284 (The Pile)

Max Activating Token Index: 897

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 1.9792. Min Range: -1.9792

Max Act: 1.9792. Min Act: -0.1700

Data Index: 392 (The Pile)

Max Activating Token Index: 521

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 1.9792. Min Range: -1.9792

Max Act: 1.9792. Min Act: -0.1700

Data Index: 76 (The Pile)

Max Activating Token Index: 93

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 1.9792. Min Range: -1.9792

Max Act: 1.9792. Min Act: -0.1700

Data Index: 250 (The Pile)

Max Activating Token Index: 911

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 1.9792. Min Range: -1.9792

Max Act: 1.9792. Min Act: -0.1700

Data Index: 278 (The Pile)

Max Activating Token Index: 623

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 1.9792. Min Range: -1.9792

Max Act: 1.9792. Min Act: -0.1700

Data Index: 140 (The Pile)

Max Activating Token Index: 352

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 1.9792. Min Range: -1.9792

Max Act: 1.9792. Min Act: -0.1700

Data Index: 245 (The Pile)

Max Activating Token Index: 223

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 1.9792. Min Range: -1.9792

Max Act: 1.9792. Min Act: -0.1700

Data Index: 287 (The Pile)

Max Activating Token Index: 897

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 1.9792. Min Range: -1.9792

Max Act: 1.9792. Min Act: -0.1700

Data Index: 1 (The Pile)

Max Activating Token Index: 370

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 1.9792. Min Range: -1.9792

Max Act: 1.9792. Min Act: -0.1700

Data Index: 107 (The Pile)

Max Activating Token Index: 936

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 1.9792. Min Range: -1.9792

Max Act: 1.9792. Min Act: -0.1700

Data Index: 368 (The Pile)

Max Activating Token Index: 264

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 1.9792. Min Range: -1.9792

Max Act: 1.9792. Min Act: -0.1700

Data Index: 27 (The Pile)

Max Activating Token Index: 448

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 1.9792. Min Range: -1.9792

Max Act: 1.9792. Min Act: -0.1700

Data Index: 226 (The Pile)

Max Activating Token Index: 74

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 1.9792. Min Range: -1.9792

Max Act: 1.9792. Min Act: -0.1700

Data Index: 157 (The Pile)

Max Activating Token Index: 264

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 1.9792. Min Range: -1.9792

Max Act: 1.9792. Min Act: -0.1700

Data Index: 89 (The Pile)

Max Activating Token Index: 666

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 1.9792. Min Range: -1.9792

Max Act: 1.9792. Min Act: -0.1700

Data Index: 271 (The Pile)

Max Activating Token Index: 232

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 1.9792. Min Range: -1.9792

Max Act: 1.9792. Min Act: -0.1700

Data Index: 342 (The Pile)

Max Activating Token Index: 56

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 1.9792. Min Range: -1.9792

Max Act: 1.9792. Min Act: -0.1700

Data Index: 280 (The Pile)

Max Activating Token Index: 429

Click toggle to see full text

Truncated

Full Text #19