< Prev | Home | Model | Random | Next >

Model: SoLU Model: 2 Layers, 2944 Neurons per Layer

Dataset: The Pile

Neuron 2689 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l-pile')



Text #0

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0244. Min Act: -0.0003

Data Index: 597009 (The Pile)

Max Activating Token Index: 6

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0242. Min Act: -0.0003

Data Index: 606460 (The Pile)

Max Activating Token Index: 9

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0233. Min Act: -0.0003

Data Index: 299890 (The Pile)

Max Activating Token Index: 6

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0226. Min Act: -0.0003

Data Index: 622651 (The Pile)

Max Activating Token Index: 5

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0231. Min Act: -0.0003

Data Index: 797957 (The Pile)

Max Activating Token Index: 7

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0225. Min Act: -0.0003

Data Index: 1596506 (The Pile)

Max Activating Token Index: 6

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0224. Min Act: -0.0003

Data Index: 517832 (The Pile)

Max Activating Token Index: 7

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0228. Min Act: -0.0003

Data Index: 484314 (The Pile)

Max Activating Token Index: 5

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0227. Min Act: -0.0003

Data Index: 1327946 (The Pile)

Max Activating Token Index: 6

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0226. Min Act: -0.0003

Data Index: 559612 (The Pile)

Max Activating Token Index: 6

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0226. Min Act: -0.0003

Data Index: 234326 (The Pile)

Max Activating Token Index: 6

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0226. Min Act: -0.0003

Data Index: 27749 (The Pile)

Max Activating Token Index: 6

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0222. Min Act: -0.0003

Data Index: 1455226 (The Pile)

Max Activating Token Index: 7

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0222. Min Act: -0.0003

Data Index: 1405766 (The Pile)

Max Activating Token Index: 7

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0222. Min Act: -0.0003

Data Index: 1762869 (The Pile)

Max Activating Token Index: 7

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0226. Min Act: -0.0003

Data Index: 1221450 (The Pile)

Max Activating Token Index: 7

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0226. Min Act: -0.0003

Data Index: 457594 (The Pile)

Max Activating Token Index: 7

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0225. Min Act: -0.0003

Data Index: 1905878 (The Pile)

Max Activating Token Index: 5

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0228. Min Act: -0.0003

Data Index: 1601704 (The Pile)

Max Activating Token Index: 6

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0219. Min Act: -0.0003

Data Index: 650552 (The Pile)

Max Activating Token Index: 976

Click toggle to see full text

Truncated

Full Text #19