< Prev | Home | Model | Random | Next >

Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 39 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')



Text #0

Max Range: 0.5820. Min Range: -0.5820

Max Act: 0.5820. Min Act: -0.0001

Data Index: 1531286 (The Pile)

Max Activating Token Index: 886

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.5820. Min Range: -0.5820

Max Act: 0.4800. Min Act: -0.0001

Data Index: 1584778 (The Pile)

Max Activating Token Index: 991

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.5820. Min Range: -0.5820

Max Act: 0.4395. Min Act: -0.0001

Data Index: 1147191 (The Pile)

Max Activating Token Index: 503

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.5820. Min Range: -0.5820

Max Act: 0.3789. Min Act: -0.0000

Data Index: 1077553 (The Pile)

Max Activating Token Index: 582

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.5820. Min Range: -0.5820

Max Act: 0.3850. Min Act: -0.0000

Data Index: 1894572 (The Pile)

Max Activating Token Index: 939

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.5820. Min Range: -0.5820

Max Act: 0.3967. Min Act: -0.0001

Data Index: 466409 (The Pile)

Max Activating Token Index: 845

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.5820. Min Range: -0.5820

Max Act: 0.3249. Min Act: -0.0001

Data Index: 1281692 (The Pile)

Max Activating Token Index: 771

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.5820. Min Range: -0.5820

Max Act: 0.3466. Min Act: -0.0001

Data Index: 1607063 (The Pile)

Max Activating Token Index: 239

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.5820. Min Range: -0.5820

Max Act: 0.3584. Min Act: -0.0001

Data Index: 289141 (The Pile)

Max Activating Token Index: 232

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.5820. Min Range: -0.5820

Max Act: 0.3611. Min Act: -0.0001

Data Index: 676021 (The Pile)

Max Activating Token Index: 748

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.5820. Min Range: -0.5820

Max Act: 0.3677. Min Act: -0.0000

Data Index: 695232 (The Pile)

Max Activating Token Index: 430

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.5820. Min Range: -0.5820

Max Act: 0.3364. Min Act: -0.0001

Data Index: 263508 (The Pile)

Max Activating Token Index: 407

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.5820. Min Range: -0.5820

Max Act: 0.3068. Min Act: -0.0001

Data Index: 1244449 (The Pile)

Max Activating Token Index: 878

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.5820. Min Range: -0.5820

Max Act: 0.3094. Min Act: -0.0001

Data Index: 485568 (The Pile)

Max Activating Token Index: 1012

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.5820. Min Range: -0.5820

Max Act: 0.3509. Min Act: -0.0001

Data Index: 249372 (The Pile)

Max Activating Token Index: 201

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.5820. Min Range: -0.5820

Max Act: 0.3039. Min Act: -0.0001

Data Index: 297391 (The Pile)

Max Activating Token Index: 986

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.5820. Min Range: -0.5820

Max Act: 0.2855. Min Act: -0.0001

Data Index: 1776501 (The Pile)

Max Activating Token Index: 110

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.5820. Min Range: -0.5820

Max Act: 0.3176. Min Act: -0.0000

Data Index: 1344617 (The Pile)

Max Activating Token Index: 606

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.5820. Min Range: -0.5820

Max Act: 0.3206. Min Act: -0.0001

Data Index: 1951852 (The Pile)

Max Activating Token Index: 245

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.5820. Min Range: -0.5820

Max Act: 0.3240. Min Act: -0.0001

Data Index: 443356 (The Pile)

Max Activating Token Index: 18

Click toggle to see full text

Truncated

Full Text #19