< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 3057 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: 2.5348. Min Range: -2.5348

Max Act: 2.5348. Min Act: -0.1700

Data Index: 9180677 (The Pile)

Max Activating Token Index: 490

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 2.5348. Min Range: -2.5348

Max Act: 2.5187. Min Act: -0.1700

Data Index: 9654369 (The Pile)

Max Activating Token Index: 830

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 2.5348. Min Range: -2.5348

Max Act: 2.5025. Min Act: -0.1700

Data Index: 2037691 (The Pile)

Max Activating Token Index: 931

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 2.5348. Min Range: -2.5348

Max Act: 2.5025. Min Act: -0.1700

Data Index: 9908840 (The Pile)

Max Activating Token Index: 998

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 2.5348. Min Range: -2.5348

Max Act: 2.4213. Min Act: -0.1700

Data Index: 7977804 (The Pile)

Max Activating Token Index: 221

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 2.5348. Min Range: -2.5348

Max Act: 2.4050. Min Act: -0.1700

Data Index: 10395443 (The Pile)

Max Activating Token Index: 289

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 2.5348. Min Range: -2.5348

Max Act: 2.4050. Min Act: -0.1700

Data Index: 9187205 (The Pile)

Max Activating Token Index: 563

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 2.5348. Min Range: -2.5348

Max Act: 2.3887. Min Act: -0.1700

Data Index: 8334526 (The Pile)

Max Activating Token Index: 688

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 2.5348. Min Range: -2.5348

Max Act: 2.3887. Min Act: -0.1700

Data Index: 9767774 (The Pile)

Max Activating Token Index: 699

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 2.5348. Min Range: -2.5348

Max Act: 2.3887. Min Act: -0.1700

Data Index: 1607974 (The Pile)

Max Activating Token Index: 614

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 2.5348. Min Range: -2.5348

Max Act: 2.3724. Min Act: -0.1700

Data Index: 1378321 (The Pile)

Max Activating Token Index: 910

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 2.5348. Min Range: -2.5348

Max Act: 2.3724. Min Act: -0.1700

Data Index: 9143576 (The Pile)

Max Activating Token Index: 792

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 2.5348. Min Range: -2.5348

Max Act: 2.3724. Min Act: -0.1700

Data Index: 1912660 (The Pile)

Max Activating Token Index: 694

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 2.5348. Min Range: -2.5348

Max Act: 2.3724. Min Act: -0.1700

Data Index: 2858046 (The Pile)

Max Activating Token Index: 376

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 2.5348. Min Range: -2.5348

Max Act: 2.3724. Min Act: -0.1700

Data Index: 8085046 (The Pile)

Max Activating Token Index: 873

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 2.5348. Min Range: -2.5348

Max Act: 2.3560. Min Act: -0.1700

Data Index: 6262180 (The Pile)

Max Activating Token Index: 315

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 2.5348. Min Range: -2.5348

Max Act: 2.3396. Min Act: -0.1700

Data Index: 1118515 (The Pile)

Max Activating Token Index: 679

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 2.5348. Min Range: -2.5348

Max Act: 2.3396. Min Act: -0.1700

Data Index: 7206457 (The Pile)

Max Activating Token Index: 580

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 2.5348. Min Range: -2.5348

Max Act: 2.3396. Min Act: -0.1700

Data Index: 8423931 (The Pile)

Max Activating Token Index: 311

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 2.5348. Min Range: -2.5348

Max Act: 2.3232. Min Act: -0.1700

Data Index: 2839625 (The Pile)

Max Activating Token Index: 416

Click toggle to see full text

Truncated

Full Text #19