Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 0 in Layer 21

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-350m')



Text #0

Max Range: 3.7991. Min Range: -3.7991

Max Act: 3.7991. Min Act: -0.1700

Data Index: 601421 (The Pile)

Max Activating Token Index: 17

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 3.7991. Min Range: -3.7991

Max Act: 3.7834. Min Act: -0.1700

Data Index: 7472245 (The Pile)

Max Activating Token Index: 437

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 3.7991. Min Range: -3.7991

Max Act: 3.7521. Min Act: -0.1700

Data Index: 6724527 (The Pile)

Max Activating Token Index: 997

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 3.7991. Min Range: -3.7991

Max Act: 3.7521. Min Act: -0.1700

Data Index: 5928701 (The Pile)

Max Activating Token Index: 283

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 3.7991. Min Range: -3.7991

Max Act: 3.7365. Min Act: -0.1700

Data Index: 8129562 (The Pile)

Max Activating Token Index: 132

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 3.7991. Min Range: -3.7991

Max Act: 3.7365. Min Act: -0.1700

Data Index: 905229 (The Pile)

Max Activating Token Index: 1011

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 3.7991. Min Range: -3.7991

Max Act: 3.7052. Min Act: -0.1700

Data Index: 8141715 (The Pile)

Max Activating Token Index: 722

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 3.7991. Min Range: -3.7991

Max Act: 3.7052. Min Act: -0.1700

Data Index: 1628587 (The Pile)

Max Activating Token Index: 340

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 3.7991. Min Range: -3.7991

Max Act: 3.6582. Min Act: -0.1700

Data Index: 6054762 (The Pile)

Max Activating Token Index: 289

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 3.7991. Min Range: -3.7991

Max Act: 3.6426. Min Act: -0.1700

Data Index: 8917752 (The Pile)

Max Activating Token Index: 259

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 3.7991. Min Range: -3.7991

Max Act: 3.6426. Min Act: -0.1700

Data Index: 7498788 (The Pile)

Max Activating Token Index: 895

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 3.7991. Min Range: -3.7991

Max Act: 3.6113. Min Act: -0.1700

Data Index: 427249 (The Pile)

Max Activating Token Index: 637

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 3.7991. Min Range: -3.7991

Max Act: 3.6113. Min Act: -0.1700

Data Index: 8105061 (The Pile)

Max Activating Token Index: 92

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 3.7991. Min Range: -3.7991

Max Act: 3.6113. Min Act: -0.1700

Data Index: 9055208 (The Pile)

Max Activating Token Index: 287

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 3.7991. Min Range: -3.7991

Max Act: 3.6113. Min Act: -0.1700

Data Index: 1177722 (The Pile)

Max Activating Token Index: 234

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 3.7991. Min Range: -3.7991

Max Act: 3.6113. Min Act: -0.1700

Data Index: 4019130 (The Pile)

Max Activating Token Index: 498

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 3.7991. Min Range: -3.7991

Max Act: 3.6113. Min Act: -0.1700

Data Index: 706988 (The Pile)

Max Activating Token Index: 987

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 3.7991. Min Range: -3.7991

Max Act: 3.6113. Min Act: -0.1700

Data Index: 5827773 (The Pile)

Max Activating Token Index: 341

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 3.7991. Min Range: -3.7991

Max Act: 3.6113. Min Act: -0.1700

Data Index: 4867203 (The Pile)

Max Activating Token Index: 240

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 3.7991. Min Range: -3.7991

Max Act: 3.6113. Min Act: -0.1700

Data Index: 1218977 (The Pile)

Max Activating Token Index: 799

Click toggle to see full text

Truncated

Full Text #19