< Prev | Home | Model | Random | Next >

Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 3034 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')



Text #0

Max Range: 1.7363. Min Range: -1.7363

Max Act: 1.7363. Min Act: 0.0000

Data Index: 1125057 (The Pile)

Max Activating Token Index: 28

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 1.7363. Min Range: -1.7363

Max Act: 1.6975. Min Act: -0.0001

Data Index: 74109 (The Pile)

Max Activating Token Index: 750

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 1.7363. Min Range: -1.7363

Max Act: 1.6282. Min Act: -0.0000

Data Index: 983072 (The Pile)

Max Activating Token Index: 433

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 1.7363. Min Range: -1.7363

Max Act: 1.3717. Min Act: 0.0001

Data Index: 1830384 (The Pile)

Max Activating Token Index: 31

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 1.7363. Min Range: -1.7363

Max Act: 1.4785. Min Act: -0.0001

Data Index: 438177 (The Pile)

Max Activating Token Index: 1009

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 1.7363. Min Range: -1.7363

Max Act: 1.5971. Min Act: -0.0000

Data Index: 1685749 (The Pile)

Max Activating Token Index: 210

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 1.7363. Min Range: -1.7363

Max Act: 1.4115. Min Act: -0.0000

Data Index: 9878 (The Pile)

Max Activating Token Index: 785

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 1.7363. Min Range: -1.7363

Max Act: 1.3878. Min Act: -0.0000

Data Index: 783215 (The Pile)

Max Activating Token Index: 238

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 1.7363. Min Range: -1.7363

Max Act: 1.4281. Min Act: -0.0001

Data Index: 1740946 (The Pile)

Max Activating Token Index: 64

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 1.7363. Min Range: -1.7363

Max Act: 1.3763. Min Act: -0.0000

Data Index: 743208 (The Pile)

Max Activating Token Index: 130

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 1.7363. Min Range: -1.7363

Max Act: 1.5057. Min Act: -0.0001

Data Index: 829568 (The Pile)

Max Activating Token Index: 464

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 1.7363. Min Range: -1.7363

Max Act: 1.4878. Min Act: 0.0001

Data Index: 1130345 (The Pile)

Max Activating Token Index: 43

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 1.7363. Min Range: -1.7363

Max Act: 1.2613. Min Act: -0.0000

Data Index: 1824848 (The Pile)

Max Activating Token Index: 40

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 1.7363. Min Range: -1.7363

Max Act: 1.3999. Min Act: -0.0001

Data Index: 1626905 (The Pile)

Max Activating Token Index: 22

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 1.7363. Min Range: -1.7363

Max Act: 1.4428. Min Act: 0.0000

Data Index: 1187392 (The Pile)

Max Activating Token Index: 19

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 1.7363. Min Range: -1.7363

Max Act: 1.3488. Min Act: -0.0000

Data Index: 1520817 (The Pile)

Max Activating Token Index: 484

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 1.7363. Min Range: -1.7363

Max Act: 1.1877. Min Act: -0.0000

Data Index: 1601125 (The Pile)

Max Activating Token Index: 911

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 1.7363. Min Range: -1.7363

Max Act: 1.3794. Min Act: -0.0001

Data Index: 1483706 (The Pile)

Max Activating Token Index: 429

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 1.7363. Min Range: -1.7363

Max Act: 1.3732. Min Act: -0.0000

Data Index: 1697067 (The Pile)

Max Activating Token Index: 718

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 1.7363. Min Range: -1.7363

Max Act: 1.3852. Min Act: -0.0001

Data Index: 1565836 (The Pile)

Max Activating Token Index: 602

Click toggle to see full text

Truncated

Full Text #19