< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 3027 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 3.2754. Min Range: -3.2754

Max Act: 3.2754. Min Act: -0.1700

Data Index: 9137240 (The Pile)

Max Activating Token Index: 470

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 3.2754. Min Range: -3.2754

Max Act: 3.2754. Min Act: -0.1700

Data Index: 7618008 (The Pile)

Max Activating Token Index: 387

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 3.2754. Min Range: -3.2754

Max Act: 3.2597. Min Act: -0.1700

Data Index: 7960244 (The Pile)

Max Activating Token Index: 70

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 3.2754. Min Range: -3.2754

Max Act: 3.2125. Min Act: -0.1700

Data Index: 3560565 (The Pile)

Max Activating Token Index: 1010

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 3.2754. Min Range: -3.2754

Max Act: 3.1968. Min Act: -0.1700

Data Index: 4476433 (The Pile)

Max Activating Token Index: 71

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 3.2754. Min Range: -3.2754

Max Act: 3.1810. Min Act: -0.1700

Data Index: 2669821 (The Pile)

Max Activating Token Index: 3

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 3.2754. Min Range: -3.2754

Max Act: 3.1653. Min Act: -0.1700

Data Index: 835004 (The Pile)

Max Activating Token Index: 617

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 3.2754. Min Range: -3.2754

Max Act: 3.1653. Min Act: -0.1700

Data Index: 2426175 (The Pile)

Max Activating Token Index: 772

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 3.2754. Min Range: -3.2754

Max Act: 3.1495. Min Act: -0.1700

Data Index: 1969415 (The Pile)

Max Activating Token Index: 399

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 3.2754. Min Range: -3.2754

Max Act: 3.1495. Min Act: -0.1700

Data Index: 993493 (The Pile)

Max Activating Token Index: 346

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 3.2754. Min Range: -3.2754

Max Act: 3.1495. Min Act: -0.1700

Data Index: 112272 (The Pile)

Max Activating Token Index: 974

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 3.2754. Min Range: -3.2754

Max Act: 3.1338. Min Act: -0.1700

Data Index: 1118882 (The Pile)

Max Activating Token Index: 745

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 3.2754. Min Range: -3.2754

Max Act: 3.1338. Min Act: -0.1700

Data Index: 7394033 (The Pile)

Max Activating Token Index: 164

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 3.2754. Min Range: -3.2754

Max Act: 3.1338. Min Act: -0.1700

Data Index: 5783282 (The Pile)

Max Activating Token Index: 842

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 3.2754. Min Range: -3.2754

Max Act: 3.1338. Min Act: -0.1700

Data Index: 8852146 (The Pile)

Max Activating Token Index: 141

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 3.2754. Min Range: -3.2754

Max Act: 3.1180. Min Act: -0.1700

Data Index: 167640 (The Pile)

Max Activating Token Index: 138

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 3.2754. Min Range: -3.2754

Max Act: 3.1180. Min Act: -0.1700

Data Index: 1923095 (The Pile)

Max Activating Token Index: 438

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 3.2754. Min Range: -3.2754

Max Act: 3.1180. Min Act: -0.1700

Data Index: 5540922 (The Pile)

Max Activating Token Index: 387

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 3.2754. Min Range: -3.2754

Max Act: 3.1180. Min Act: -0.1700

Data Index: 4446960 (The Pile)

Max Activating Token Index: 998

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 3.2754. Min Range: -3.2754

Max Act: 3.1180. Min Act: -0.1700

Data Index: 10633633 (The Pile)

Max Activating Token Index: 392

Click toggle to see full text

Truncated

Full Text #19