< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 5101 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 1.5663. Min Range: -1.5663

Max Act: 1.5663. Min Act: -0.0000

Data Index: 629345 (The Pile)

Max Activating Token Index: 293

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 1.5663. Min Range: -1.5663

Max Act: 1.2824. Min Act: -0.0000

Data Index: 1350710 (The Pile)

Max Activating Token Index: 193

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 1.5663. Min Range: -1.5663

Max Act: 1.3219. Min Act: -0.0000

Data Index: 1365886 (The Pile)

Max Activating Token Index: 937

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 1.5663. Min Range: -1.5663

Max Act: 1.2489. Min Act: -0.0000

Data Index: 1119872 (The Pile)

Max Activating Token Index: 220

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 1.5663. Min Range: -1.5663

Max Act: 1.2265. Min Act: -0.0000

Data Index: 1462330 (The Pile)

Max Activating Token Index: 651

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 1.5663. Min Range: -1.5663

Max Act: 1.2265. Min Act: -0.0000

Data Index: 171087 (The Pile)

Max Activating Token Index: 464

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 1.5663. Min Range: -1.5663

Max Act: 1.2134. Min Act: -0.0000

Data Index: 1524940 (The Pile)

Max Activating Token Index: 761

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 1.5663. Min Range: -1.5663

Max Act: 1.0881. Min Act: -0.0000

Data Index: 627883 (The Pile)

Max Activating Token Index: 639

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 1.5663. Min Range: -1.5663

Max Act: 1.1906. Min Act: -0.0000

Data Index: 477504 (The Pile)

Max Activating Token Index: 970

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 1.5663. Min Range: -1.5663

Max Act: 1.1196. Min Act: -0.0000

Data Index: 1293430 (The Pile)

Max Activating Token Index: 367

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 1.5663. Min Range: -1.5663

Max Act: 1.0341. Min Act: -0.0000

Data Index: 1597462 (The Pile)

Max Activating Token Index: 246

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 1.5663. Min Range: -1.5663

Max Act: 1.0872. Min Act: -0.0000

Data Index: 602261 (The Pile)

Max Activating Token Index: 184

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 1.5663. Min Range: -1.5663

Max Act: 1.0909. Min Act: -0.0000

Data Index: 795843 (The Pile)

Max Activating Token Index: 918

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 1.5663. Min Range: -1.5663

Max Act: 1.0883. Min Act: -0.0000

Data Index: 241334 (The Pile)

Max Activating Token Index: 611

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 1.5663. Min Range: -1.5663

Max Act: 1.1137. Min Act: -0.0000

Data Index: 1114224 (The Pile)

Max Activating Token Index: 102

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 1.5663. Min Range: -1.5663

Max Act: 0.9789. Min Act: -0.0000

Data Index: 49187 (The Pile)

Max Activating Token Index: 420

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 1.5663. Min Range: -1.5663

Max Act: 1.0270. Min Act: -0.0000

Data Index: 1214561 (The Pile)

Max Activating Token Index: 104

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 1.5663. Min Range: -1.5663

Max Act: 1.0584. Min Act: -0.0000

Data Index: 1724564 (The Pile)

Max Activating Token Index: 240

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 1.5663. Min Range: -1.5663

Max Act: 1.0496. Min Act: -0.0000

Data Index: 803534 (The Pile)

Max Activating Token Index: 322

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 1.5663. Min Range: -1.5663

Max Act: 1.0684. Min Act: -0.0000

Data Index: 1405937 (The Pile)

Max Activating Token Index: 307

Click toggle to see full text

Truncated

Full Text #19