< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 11 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: 2.6970. Min Range: -2.6970

Max Act: 2.6124. Min Act: -0.0000

Data Index: 1270569 (The Pile)

Max Activating Token Index: 378

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 2.6970. Min Range: -2.6970

Max Act: 2.6970. Min Act: -0.0000

Data Index: 1711075 (The Pile)

Max Activating Token Index: 792

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 2.6970. Min Range: -2.6970

Max Act: 2.4742. Min Act: -0.0000

Data Index: 104730 (The Pile)

Max Activating Token Index: 502

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 2.6970. Min Range: -2.6970

Max Act: 2.4471. Min Act: -0.0000

Data Index: 449582 (The Pile)

Max Activating Token Index: 634

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 2.6970. Min Range: -2.6970

Max Act: 2.5471. Min Act: -0.0000

Data Index: 1095642 (The Pile)

Max Activating Token Index: 986

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 2.6970. Min Range: -2.6970

Max Act: 2.2769. Min Act: -0.0000

Data Index: 416990 (The Pile)

Max Activating Token Index: 704

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 2.6970. Min Range: -2.6970

Max Act: 2.3980. Min Act: -0.0000

Data Index: 1649176 (The Pile)

Max Activating Token Index: 13

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 2.6970. Min Range: -2.6970

Max Act: 2.3294. Min Act: -0.0000

Data Index: 269658 (The Pile)

Max Activating Token Index: 973

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 2.6970. Min Range: -2.6970

Max Act: 2.1812. Min Act: -0.0000

Data Index: 1661978 (The Pile)

Max Activating Token Index: 155

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 2.6970. Min Range: -2.6970

Max Act: 2.2716. Min Act: -0.0000

Data Index: 308677 (The Pile)

Max Activating Token Index: 510

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 2.6970. Min Range: -2.6970

Max Act: 2.1387. Min Act: -0.0000

Data Index: 203197 (The Pile)

Max Activating Token Index: 993

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 2.6970. Min Range: -2.6970

Max Act: 2.0229. Min Act: -0.0000

Data Index: 798973 (The Pile)

Max Activating Token Index: 790

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 2.6970. Min Range: -2.6970

Max Act: 2.2487. Min Act: -0.0000

Data Index: 940505 (The Pile)

Max Activating Token Index: 48

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 2.6970. Min Range: -2.6970

Max Act: 2.2229. Min Act: -0.0000

Data Index: 1484146 (The Pile)

Max Activating Token Index: 470

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 2.6970. Min Range: -2.6970

Max Act: 2.2084. Min Act: -0.0000

Data Index: 1392619 (The Pile)

Max Activating Token Index: 343

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 2.6970. Min Range: -2.6970

Max Act: 2.3274. Min Act: -0.0000

Data Index: 328196 (The Pile)

Max Activating Token Index: 173

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 2.6970. Min Range: -2.6970

Max Act: 2.1838. Min Act: -0.0000

Data Index: 1209296 (The Pile)

Max Activating Token Index: 859

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 2.6970. Min Range: -2.6970

Max Act: 2.0699. Min Act: -0.0000

Data Index: 1381463 (The Pile)

Max Activating Token Index: 95

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 2.6970. Min Range: -2.6970

Max Act: 2.0747. Min Act: -0.0000

Data Index: 633567 (The Pile)

Max Activating Token Index: 269

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 2.6970. Min Range: -2.6970

Max Act: 2.1868. Min Act: -0.0000

Data Index: 1430748 (The Pile)

Max Activating Token Index: 341

Click toggle to see full text

Truncated

Full Text #19