< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 32 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 3.2989. Min Range: -3.2989

Max Act: 2.5904. Min Act: -0.0000

Data Index: 1553788 (The Pile)

Max Activating Token Index: 842

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 3.2989. Min Range: -3.2989

Max Act: 2.9396. Min Act: -0.0000

Data Index: 1581278 (The Pile)

Max Activating Token Index: 638

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 3.2989. Min Range: -3.2989

Max Act: 3.2158. Min Act: -0.0000

Data Index: 1773830 (The Pile)

Max Activating Token Index: 172

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 3.2989. Min Range: -3.2989

Max Act: 3.0540. Min Act: -0.0000

Data Index: 606731 (The Pile)

Max Activating Token Index: 263

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 3.2989. Min Range: -3.2989

Max Act: 2.5624. Min Act: -0.0000

Data Index: 896194 (The Pile)

Max Activating Token Index: 899

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 3.2989. Min Range: -3.2989

Max Act: 2.9017. Min Act: -0.0000

Data Index: 151693 (The Pile)

Max Activating Token Index: 359

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 3.2989. Min Range: -3.2989

Max Act: 2.0739. Min Act: -0.0000

Data Index: 1899622 (The Pile)

Max Activating Token Index: 54

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 3.2989. Min Range: -3.2989

Max Act: 2.6909. Min Act: -0.0000

Data Index: 369636 (The Pile)

Max Activating Token Index: 243

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 3.2989. Min Range: -3.2989

Max Act: 3.2989. Min Act: -0.0000

Data Index: 227589 (The Pile)

Max Activating Token Index: 825

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 3.2989. Min Range: -3.2989

Max Act: 2.5206. Min Act: -0.0000

Data Index: 595518 (The Pile)

Max Activating Token Index: 343

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 3.2989. Min Range: -3.2989

Max Act: 2.3793. Min Act: -0.0000

Data Index: 1047362 (The Pile)

Max Activating Token Index: 533

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 3.2989. Min Range: -3.2989

Max Act: 2.1738. Min Act: -0.0000

Data Index: 843000 (The Pile)

Max Activating Token Index: 140

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 3.2989. Min Range: -3.2989

Max Act: 2.5717. Min Act: -0.0000

Data Index: 1267533 (The Pile)

Max Activating Token Index: 731

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 3.2989. Min Range: -3.2989

Max Act: 2.7804. Min Act: -0.0000

Data Index: 1021284 (The Pile)

Max Activating Token Index: 199

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 3.2989. Min Range: -3.2989

Max Act: 2.6101. Min Act: -0.0000

Data Index: 1070839 (The Pile)

Max Activating Token Index: 308

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 3.2989. Min Range: -3.2989

Max Act: 2.7140. Min Act: -0.0000

Data Index: 114724 (The Pile)

Max Activating Token Index: 386

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 3.2989. Min Range: -3.2989

Max Act: 2.7144. Min Act: -0.0000

Data Index: 835115 (The Pile)

Max Activating Token Index: 215

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 3.2989. Min Range: -3.2989

Max Act: 2.4916. Min Act: -0.0000

Data Index: 772639 (The Pile)

Max Activating Token Index: 326

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 3.2989. Min Range: -3.2989

Max Act: 2.4869. Min Act: -0.0000

Data Index: 12779 (The Pile)

Max Activating Token Index: 268

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 3.2989. Min Range: -3.2989

Max Act: 2.4139. Min Act: -0.0000

Data Index: 1689043 (The Pile)

Max Activating Token Index: 530

Click toggle to see full text

Truncated

Full Text #19