< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 5106 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 2.2138. Min Range: -2.2138

Max Act: 2.2138. Min Act: -0.0000

Data Index: 1535582 (The Pile)

Max Activating Token Index: 783

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 2.2138. Min Range: -2.2138

Max Act: 1.7847. Min Act: -0.0000

Data Index: 98636 (The Pile)

Max Activating Token Index: 922

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 2.2138. Min Range: -2.2138

Max Act: 1.5927. Min Act: -0.0000

Data Index: 699312 (The Pile)

Max Activating Token Index: 198

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 2.2138. Min Range: -2.2138

Max Act: 1.5133. Min Act: -0.0000

Data Index: 1440049 (The Pile)

Max Activating Token Index: 258

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 2.2138. Min Range: -2.2138

Max Act: 1.1119. Min Act: -0.0000

Data Index: 872847 (The Pile)

Max Activating Token Index: 994

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 2.2138. Min Range: -2.2138

Max Act: 1.1454. Min Act: -0.0000

Data Index: 673407 (The Pile)

Max Activating Token Index: 485

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 2.2138. Min Range: -2.2138

Max Act: 1.1502. Min Act: -0.0000

Data Index: 694487 (The Pile)

Max Activating Token Index: 566

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 2.2138. Min Range: -2.2138

Max Act: 1.2736. Min Act: -0.0000

Data Index: 1459403 (The Pile)

Max Activating Token Index: 774

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 2.2138. Min Range: -2.2138

Max Act: 1.0977. Min Act: -0.0000

Data Index: 1198273 (The Pile)

Max Activating Token Index: 800

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 2.2138. Min Range: -2.2138

Max Act: 1.1707. Min Act: -0.0000

Data Index: 1671306 (The Pile)

Max Activating Token Index: 991

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 2.2138. Min Range: -2.2138

Max Act: 1.0714. Min Act: -0.0000

Data Index: 835454 (The Pile)

Max Activating Token Index: 875

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 2.2138. Min Range: -2.2138

Max Act: 0.9360. Min Act: -0.0000

Data Index: 541143 (The Pile)

Max Activating Token Index: 798

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 2.2138. Min Range: -2.2138

Max Act: 1.0946. Min Act: -0.0000

Data Index: 187019 (The Pile)

Max Activating Token Index: 262

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 2.2138. Min Range: -2.2138

Max Act: 1.1569. Min Act: -0.0000

Data Index: 417197 (The Pile)

Max Activating Token Index: 223

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 2.2138. Min Range: -2.2138

Max Act: 1.0831. Min Act: -0.0000

Data Index: 591182 (The Pile)

Max Activating Token Index: 470

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 2.2138. Min Range: -2.2138

Max Act: 1.0800. Min Act: -0.0000

Data Index: 1855320 (The Pile)

Max Activating Token Index: 365

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 2.2138. Min Range: -2.2138

Max Act: 1.0768. Min Act: -0.0000

Data Index: 1841959 (The Pile)

Max Activating Token Index: 343

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 2.2138. Min Range: -2.2138

Max Act: 1.1005. Min Act: -0.0000

Data Index: 1263418 (The Pile)

Max Activating Token Index: 74

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 2.2138. Min Range: -2.2138

Max Act: 0.9486. Min Act: -0.0000

Data Index: 1651948 (The Pile)

Max Activating Token Index: 95

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 2.2138. Min Range: -2.2138

Max Act: 0.9200. Min Act: -0.0000

Data Index: 1851098 (The Pile)

Max Activating Token Index: 69

Click toggle to see full text

Truncated

Full Text #19