< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 2987 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: 3.4596. Min Range: -3.4596

Max Act: 3.4596. Min Act: -0.1700

Data Index: 3817531 (The Pile)

Max Activating Token Index: 460

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 3.4596. Min Range: -3.4596

Max Act: 3.4596. Min Act: -0.1700

Data Index: 8444461 (The Pile)

Max Activating Token Index: 903

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 3.4596. Min Range: -3.4596

Max Act: 3.4439. Min Act: -0.1700

Data Index: 7869681 (The Pile)

Max Activating Token Index: 924

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 3.4596. Min Range: -3.4596

Max Act: 3.4282. Min Act: -0.1700

Data Index: 3155805 (The Pile)

Max Activating Token Index: 533

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 3.4596. Min Range: -3.4596

Max Act: 3.4282. Min Act: -0.1700

Data Index: 9968450 (The Pile)

Max Activating Token Index: 319

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 3.4596. Min Range: -3.4596

Max Act: 3.4282. Min Act: -0.1700

Data Index: 3852102 (The Pile)

Max Activating Token Index: 681

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 3.4596. Min Range: -3.4596

Max Act: 3.4282. Min Act: -0.1700

Data Index: 9789679 (The Pile)

Max Activating Token Index: 807

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 3.4596. Min Range: -3.4596

Max Act: 3.4125. Min Act: -0.1700

Data Index: 323112 (The Pile)

Max Activating Token Index: 610

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 3.4596. Min Range: -3.4596

Max Act: 3.4125. Min Act: -0.1700

Data Index: 2838551 (The Pile)

Max Activating Token Index: 702

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 3.4596. Min Range: -3.4596

Max Act: 3.4125. Min Act: -0.1700

Data Index: 2501319 (The Pile)

Max Activating Token Index: 942

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 3.4596. Min Range: -3.4596

Max Act: 3.4125. Min Act: -0.1700

Data Index: 10122517 (The Pile)

Max Activating Token Index: 1018

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 3.4596. Min Range: -3.4596

Max Act: 3.4125. Min Act: -0.1700

Data Index: 56930 (The Pile)

Max Activating Token Index: 233

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 3.4596. Min Range: -3.4596

Max Act: 3.4125. Min Act: -0.1700

Data Index: 4807443 (The Pile)

Max Activating Token Index: 524

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 3.4596. Min Range: -3.4596

Max Act: 3.3968. Min Act: -0.1700

Data Index: 1545304 (The Pile)

Max Activating Token Index: 888

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 3.4596. Min Range: -3.4596

Max Act: 3.3968. Min Act: -0.1700

Data Index: 6921 (The Pile)

Max Activating Token Index: 631

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 3.4596. Min Range: -3.4596

Max Act: 3.3812. Min Act: -0.1700

Data Index: 6084326 (The Pile)

Max Activating Token Index: 906

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 3.4596. Min Range: -3.4596

Max Act: 3.3812. Min Act: -0.1700

Data Index: 9065416 (The Pile)

Max Activating Token Index: 978

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 3.4596. Min Range: -3.4596

Max Act: 3.3812. Min Act: -0.1700

Data Index: 8492319 (The Pile)

Max Activating Token Index: 983

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 3.4596. Min Range: -3.4596

Max Act: 3.3812. Min Act: -0.1700

Data Index: 7340146 (The Pile)

Max Activating Token Index: 1016

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 3.4596. Min Range: -3.4596

Max Act: 3.3812. Min Act: -0.1700

Data Index: 2692695 (The Pile)

Max Activating Token Index: 710

Click toggle to see full text

Truncated

Full Text #19