< Prev | Home | Model | Random | Next >

Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 19 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')



Text #0

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0844. Min Act: -0.0002

Data Index: 1339883 (The Pile)

Max Activating Token Index: 174

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0816. Min Act: -0.0001

Data Index: 329170 (The Pile)

Max Activating Token Index: 970

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0358. Min Act: -0.0002

Data Index: 1089177 (The Pile)

Max Activating Token Index: 535

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0328. Min Act: -0.0002

Data Index: 1719346 (The Pile)

Max Activating Token Index: 897

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0317. Min Act: -0.0002

Data Index: 311622 (The Pile)

Max Activating Token Index: 721

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0314. Min Act: -0.0003

Data Index: 164868 (The Pile)

Max Activating Token Index: 412

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0262. Min Act: -0.0002

Data Index: 69972 (The Pile)

Max Activating Token Index: 176

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0259. Min Act: -0.0002

Data Index: 1332846 (The Pile)

Max Activating Token Index: 518

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0238. Min Act: -0.0002

Data Index: 609419 (The Pile)

Max Activating Token Index: 667

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0227. Min Act: -0.0002

Data Index: 1394828 (The Pile)

Max Activating Token Index: 473

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0216. Min Act: -0.0002

Data Index: 1174246 (The Pile)

Max Activating Token Index: 714

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0219. Min Act: -0.0002

Data Index: 799069 (The Pile)

Max Activating Token Index: 813

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0212. Min Act: -0.0002

Data Index: 60772 (The Pile)

Max Activating Token Index: 33

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0217. Min Act: -0.0002

Data Index: 1811941 (The Pile)

Max Activating Token Index: 266

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0206. Min Act: -0.0002

Data Index: 1141854 (The Pile)

Max Activating Token Index: 737

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0205. Min Act: -0.0002

Data Index: 1751730 (The Pile)

Max Activating Token Index: 249

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0208. Min Act: -0.0002

Data Index: 1777816 (The Pile)

Max Activating Token Index: 413

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0201. Min Act: -0.0003

Data Index: 507569 (The Pile)

Max Activating Token Index: 647

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0207. Min Act: -0.0002

Data Index: 1885523 (The Pile)

Max Activating Token Index: 786

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0200. Min Act: -0.0002

Data Index: 1035827 (The Pile)

Max Activating Token Index: 301

Click toggle to see full text

Truncated

Full Text #19