< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 15 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 1.0363. Min Range: -1.0363

Max Act: 1.0363. Min Act: -0.0002

Data Index: 218622 (The Pile)

Max Activating Token Index: 662

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 1.0363. Min Range: -1.0363

Max Act: 0.8876. Min Act: -0.0002

Data Index: 1606972 (The Pile)

Max Activating Token Index: 197

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 1.0363. Min Range: -1.0363

Max Act: 0.8792. Min Act: -0.0002

Data Index: 264906 (The Pile)

Max Activating Token Index: 113

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 1.0363. Min Range: -1.0363

Max Act: 0.9897. Min Act: -0.0002

Data Index: 1641437 (The Pile)

Max Activating Token Index: 6

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 1.0363. Min Range: -1.0363

Max Act: 0.9174. Min Act: -0.0002

Data Index: 443373 (The Pile)

Max Activating Token Index: 118

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 1.0363. Min Range: -1.0363

Max Act: 0.9451. Min Act: -0.0002

Data Index: 460100 (The Pile)

Max Activating Token Index: 128

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 1.0363. Min Range: -1.0363

Max Act: 0.9138. Min Act: -0.0002

Data Index: 1310407 (The Pile)

Max Activating Token Index: 529

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 1.0363. Min Range: -1.0363

Max Act: 0.9805. Min Act: -0.0002

Data Index: 666826 (The Pile)

Max Activating Token Index: 165

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 1.0363. Min Range: -1.0363

Max Act: 0.8574. Min Act: -0.0002

Data Index: 1636097 (The Pile)

Max Activating Token Index: 145

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 1.0363. Min Range: -1.0363

Max Act: 0.9549. Min Act: -0.0002

Data Index: 1615003 (The Pile)

Max Activating Token Index: 43

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 1.0363. Min Range: -1.0363

Max Act: 0.7952. Min Act: -0.0002

Data Index: 1846186 (The Pile)

Max Activating Token Index: 94

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 1.0363. Min Range: -1.0363

Max Act: 0.6754. Min Act: -0.0002

Data Index: 1743385 (The Pile)

Max Activating Token Index: 670

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 1.0363. Min Range: -1.0363

Max Act: 0.8873. Min Act: -0.0002

Data Index: 305005 (The Pile)

Max Activating Token Index: 668

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 1.0363. Min Range: -1.0363

Max Act: 0.7806. Min Act: -0.0002

Data Index: 647142 (The Pile)

Max Activating Token Index: 151

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 1.0363. Min Range: -1.0363

Max Act: 0.7984. Min Act: -0.0002

Data Index: 1642708 (The Pile)

Max Activating Token Index: 17

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 1.0363. Min Range: -1.0363

Max Act: 0.9574. Min Act: -0.0002

Data Index: 1870109 (The Pile)

Max Activating Token Index: 107

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 1.0363. Min Range: -1.0363

Max Act: 0.7466. Min Act: -0.0002

Data Index: 1282498 (The Pile)

Max Activating Token Index: 127

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 1.0363. Min Range: -1.0363

Max Act: 0.8704. Min Act: -0.0002

Data Index: 360766 (The Pile)

Max Activating Token Index: 162

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 1.0363. Min Range: -1.0363

Max Act: 0.8418. Min Act: -0.0002

Data Index: 508760 (The Pile)

Max Activating Token Index: 13

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 1.0363. Min Range: -1.0363

Max Act: 0.9172. Min Act: -0.0002

Data Index: 286555 (The Pile)

Max Activating Token Index: 48

Click toggle to see full text

Truncated

Full Text #19