< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 7 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 0.3982. Min Range: -0.3982

Max Act: 0.3868. Min Act: -0.0000

Data Index: 1230517 (The Pile)

Max Activating Token Index: 30

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.3982. Min Range: -0.3982

Max Act: 0.3978. Min Act: -0.0001

Data Index: 10311 (The Pile)

Max Activating Token Index: 456

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.3982. Min Range: -0.3982

Max Act: 0.3528. Min Act: -0.0000

Data Index: 1906948 (The Pile)

Max Activating Token Index: 185

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.3982. Min Range: -0.3982

Max Act: 0.3916. Min Act: -0.0001

Data Index: 1754434 (The Pile)

Max Activating Token Index: 47

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.3982. Min Range: -0.3982

Max Act: 0.3682. Min Act: -0.0001

Data Index: 1063993 (The Pile)

Max Activating Token Index: 1011

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.3982. Min Range: -0.3982

Max Act: 0.3377. Min Act: -0.0000

Data Index: 412604 (The Pile)

Max Activating Token Index: 995

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.3982. Min Range: -0.3982

Max Act: 0.3776. Min Act: -0.0000

Data Index: 1676291 (The Pile)

Max Activating Token Index: 780

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.3982. Min Range: -0.3982

Max Act: 0.3678. Min Act: -0.0000

Data Index: 1926398 (The Pile)

Max Activating Token Index: 455

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.3982. Min Range: -0.3982

Max Act: 0.3834. Min Act: -0.0001

Data Index: 1358404 (The Pile)

Max Activating Token Index: 587

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.3982. Min Range: -0.3982

Max Act: 0.3438. Min Act: -0.0000

Data Index: 1781373 (The Pile)

Max Activating Token Index: 8

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.3982. Min Range: -0.3982

Max Act: 0.3514. Min Act: -0.0001

Data Index: 1227988 (The Pile)

Max Activating Token Index: 124

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.3982. Min Range: -0.3982

Max Act: 0.3982. Min Act: -0.0001

Data Index: 1618773 (The Pile)

Max Activating Token Index: 564

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.3982. Min Range: -0.3982

Max Act: 0.3534. Min Act: -0.0001

Data Index: 515137 (The Pile)

Max Activating Token Index: 43

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.3982. Min Range: -0.3982

Max Act: 0.3479. Min Act: -0.0000

Data Index: 1844171 (The Pile)

Max Activating Token Index: 75

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.3982. Min Range: -0.3982

Max Act: 0.3163. Min Act: -0.0000

Data Index: 137904 (The Pile)

Max Activating Token Index: 780

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.3982. Min Range: -0.3982

Max Act: 0.3387. Min Act: -0.0001

Data Index: 702884 (The Pile)

Max Activating Token Index: 620

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.3982. Min Range: -0.3982

Max Act: 0.3140. Min Act: -0.0001

Data Index: 370686 (The Pile)

Max Activating Token Index: 262

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.3982. Min Range: -0.3982

Max Act: 0.3365. Min Act: -0.0001

Data Index: 1354254 (The Pile)

Max Activating Token Index: 293

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.3982. Min Range: -0.3982

Max Act: 0.3577. Min Act: -0.0001

Data Index: 1871129 (The Pile)

Max Activating Token Index: 502

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.3982. Min Range: -0.3982

Max Act: 0.3295. Min Act: -0.0000

Data Index: 299304 (The Pile)

Max Activating Token Index: 975

Click toggle to see full text

Truncated

Full Text #19