< Prev | Home | Model | Random | Next >

Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 79 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')



Text #0

Max Range: 0.8739. Min Range: -0.8739

Max Act: 0.8739. Min Act: -0.0001

Data Index: 1687000 (The Pile)

Max Activating Token Index: 38

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.8739. Min Range: -0.8739

Max Act: 0.7981. Min Act: -0.0001

Data Index: 1468555 (The Pile)

Max Activating Token Index: 16

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.8739. Min Range: -0.8739

Max Act: 0.7063. Min Act: -0.0000

Data Index: 1709948 (The Pile)

Max Activating Token Index: 400

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.8739. Min Range: -0.8739

Max Act: 0.6929. Min Act: -0.0001

Data Index: 1659042 (The Pile)

Max Activating Token Index: 28

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.8739. Min Range: -0.8739

Max Act: 0.7091. Min Act: -0.0001

Data Index: 1234445 (The Pile)

Max Activating Token Index: 471

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.8739. Min Range: -0.8739

Max Act: 0.6176. Min Act: -0.0001

Data Index: 246979 (The Pile)

Max Activating Token Index: 975

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.8739. Min Range: -0.8739

Max Act: 0.7189. Min Act: -0.0001

Data Index: 1441824 (The Pile)

Max Activating Token Index: 28

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.8739. Min Range: -0.8739

Max Act: 0.7689. Min Act: -0.0001

Data Index: 1646136 (The Pile)

Max Activating Token Index: 623

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.8739. Min Range: -0.8739

Max Act: 0.6866. Min Act: -0.0001

Data Index: 432703 (The Pile)

Max Activating Token Index: 284

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.8739. Min Range: -0.8739

Max Act: 0.6281. Min Act: -0.0001

Data Index: 174130 (The Pile)

Max Activating Token Index: 850

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.8739. Min Range: -0.8739

Max Act: 0.6602. Min Act: -0.0001

Data Index: 661136 (The Pile)

Max Activating Token Index: 134

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.8739. Min Range: -0.8739

Max Act: 0.6987. Min Act: -0.0001

Data Index: 784584 (The Pile)

Max Activating Token Index: 415

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.8739. Min Range: -0.8739

Max Act: 0.6437. Min Act: -0.0001

Data Index: 929624 (The Pile)

Max Activating Token Index: 171

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.8739. Min Range: -0.8739

Max Act: 0.6789. Min Act: -0.0001

Data Index: 118666 (The Pile)

Max Activating Token Index: 157

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.8739. Min Range: -0.8739

Max Act: 0.6572. Min Act: -0.0001

Data Index: 1667815 (The Pile)

Max Activating Token Index: 27

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.8739. Min Range: -0.8739

Max Act: 0.7063. Min Act: -0.0001

Data Index: 463963 (The Pile)

Max Activating Token Index: 341

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.8739. Min Range: -0.8739

Max Act: 0.6482. Min Act: -0.0001

Data Index: 1122383 (The Pile)

Max Activating Token Index: 13

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.8739. Min Range: -0.8739

Max Act: 0.7046. Min Act: -0.0001

Data Index: 153760 (The Pile)

Max Activating Token Index: 40

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.8739. Min Range: -0.8739

Max Act: 0.6409. Min Act: -0.0001

Data Index: 1343095 (The Pile)

Max Activating Token Index: 17

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.8739. Min Range: -0.8739

Max Act: 0.6314. Min Act: -0.0001

Data Index: 689202 (The Pile)

Max Activating Token Index: 631

Click toggle to see full text

Truncated

Full Text #19