< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 14 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0242. Min Act: -0.0000

Data Index: 1759164 (The Pile)

Max Activating Token Index: 14

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0237. Min Act: -0.0000

Data Index: 1882187 (The Pile)

Max Activating Token Index: 14

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0234. Min Act: 0.0000

Data Index: 1466307 (The Pile)

Max Activating Token Index: 3

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0223. Min Act: -0.0000

Data Index: 487157 (The Pile)

Max Activating Token Index: 6

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0229. Min Act: 0.0000

Data Index: 1096914 (The Pile)

Max Activating Token Index: 4

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0226. Min Act: 0.0000

Data Index: 1648341 (The Pile)

Max Activating Token Index: 12

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0224. Min Act: -0.0000

Data Index: 1261374 (The Pile)

Max Activating Token Index: 12

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0223. Min Act: -0.0000

Data Index: 1085396 (The Pile)

Max Activating Token Index: 41

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0222. Min Act: -0.0000

Data Index: 1032623 (The Pile)

Max Activating Token Index: 6

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0215. Min Act: -0.0000

Data Index: 1702162 (The Pile)

Max Activating Token Index: 52

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0223. Min Act: -0.0000

Data Index: 788954 (The Pile)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0223. Min Act: -0.0000

Data Index: 1620589 (The Pile)

Max Activating Token Index: 54

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0222. Min Act: -0.0000

Data Index: 1769707 (The Pile)

Max Activating Token Index: 14

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0220. Min Act: 0.0000

Data Index: 21975 (The Pile)

Max Activating Token Index: 5

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0219. Min Act: -0.0000

Data Index: 1689990 (The Pile)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0219. Min Act: -0.0000

Data Index: 1450256 (The Pile)

Max Activating Token Index: 5

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0217. Min Act: 0.0000

Data Index: 1067403 (The Pile)

Max Activating Token Index: 5

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0217. Min Act: -0.0000

Data Index: 1743888 (The Pile)

Max Activating Token Index: 5

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0217. Min Act: -0.0000

Data Index: 609377 (The Pile)

Max Activating Token Index: 1004

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0226. Min Act: -0.0000

Data Index: 1387180 (The Pile)

Max Activating Token Index: 7

Click toggle to see full text

Truncated

Full Text #19