< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 5092 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: 0.4726. Min Range: -0.4726

Max Act: 0.4726. Min Act: -0.0000

Data Index: 42643 (The Pile)

Max Activating Token Index: 268

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.4726. Min Range: -0.4726

Max Act: 0.4057. Min Act: -0.0000

Data Index: 994940 (The Pile)

Max Activating Token Index: 71

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.4726. Min Range: -0.4726

Max Act: 0.3845. Min Act: -0.0000

Data Index: 1162849 (The Pile)

Max Activating Token Index: 355

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.4726. Min Range: -0.4726

Max Act: 0.3893. Min Act: -0.0000

Data Index: 672247 (The Pile)

Max Activating Token Index: 891

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.4726. Min Range: -0.4726

Max Act: 0.3671. Min Act: -0.0000

Data Index: 237156 (The Pile)

Max Activating Token Index: 825

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.4726. Min Range: -0.4726

Max Act: 0.3814. Min Act: -0.0000

Data Index: 1732614 (The Pile)

Max Activating Token Index: 523

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.4726. Min Range: -0.4726

Max Act: 0.3865. Min Act: -0.0000

Data Index: 458484 (The Pile)

Max Activating Token Index: 674

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.4726. Min Range: -0.4726

Max Act: 0.3572. Min Act: -0.0000

Data Index: 1659622 (The Pile)

Max Activating Token Index: 107

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.4726. Min Range: -0.4726

Max Act: 0.3450. Min Act: -0.0000

Data Index: 1724269 (The Pile)

Max Activating Token Index: 250

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.4726. Min Range: -0.4726

Max Act: 0.3414. Min Act: -0.0000

Data Index: 361369 (The Pile)

Max Activating Token Index: 139

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.4726. Min Range: -0.4726

Max Act: 0.3631. Min Act: -0.0000

Data Index: 1594146 (The Pile)

Max Activating Token Index: 177

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.4726. Min Range: -0.4726

Max Act: 0.3439. Min Act: -0.0000

Data Index: 1885034 (The Pile)

Max Activating Token Index: 373

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.4726. Min Range: -0.4726

Max Act: 0.3518. Min Act: -0.0000

Data Index: 538116 (The Pile)

Max Activating Token Index: 58

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.4726. Min Range: -0.4726

Max Act: 0.3633. Min Act: -0.0000

Data Index: 1863724 (The Pile)

Max Activating Token Index: 540

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.4726. Min Range: -0.4726

Max Act: 0.3232. Min Act: -0.0000

Data Index: 160424 (The Pile)

Max Activating Token Index: 1021

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.4726. Min Range: -0.4726

Max Act: 0.3356. Min Act: -0.0000

Data Index: 1343517 (The Pile)

Max Activating Token Index: 188

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.4726. Min Range: -0.4726

Max Act: 0.3298. Min Act: -0.0000

Data Index: 1930382 (The Pile)

Max Activating Token Index: 719

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.4726. Min Range: -0.4726

Max Act: 0.3191. Min Act: -0.0000

Data Index: 690050 (The Pile)

Max Activating Token Index: 464

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.4726. Min Range: -0.4726

Max Act: 0.3192. Min Act: -0.0000

Data Index: 1357732 (The Pile)

Max Activating Token Index: 126

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.4726. Min Range: -0.4726

Max Act: 0.3164. Min Act: -0.0000

Data Index: 364321 (The Pile)

Max Activating Token Index: 749

Click toggle to see full text

Truncated

Full Text #19