< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 4048 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 0.4695. Min Range: -0.4695

Max Act: 0.4695. Min Act: -0.0001

Data Index: 248724 (The Pile)

Max Activating Token Index: 936

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.4695. Min Range: -0.4695

Max Act: 0.3626. Min Act: -0.0001

Data Index: 1863968 (The Pile)

Max Activating Token Index: 671

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.4695. Min Range: -0.4695

Max Act: 0.3510. Min Act: -0.0001

Data Index: 1366183 (The Pile)

Max Activating Token Index: 757

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.4695. Min Range: -0.4695

Max Act: 0.3780. Min Act: -0.0001

Data Index: 1203857 (The Pile)

Max Activating Token Index: 830

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.4695. Min Range: -0.4695

Max Act: 0.3216. Min Act: -0.0001

Data Index: 1486656 (The Pile)

Max Activating Token Index: 875

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.4695. Min Range: -0.4695

Max Act: 0.3608. Min Act: -0.0001

Data Index: 796061 (The Pile)

Max Activating Token Index: 364

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.4695. Min Range: -0.4695

Max Act: 0.3130. Min Act: -0.0001

Data Index: 637097 (The Pile)

Max Activating Token Index: 974

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.4695. Min Range: -0.4695

Max Act: 0.3437. Min Act: -0.0001

Data Index: 1791685 (The Pile)

Max Activating Token Index: 556

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.4695. Min Range: -0.4695

Max Act: 0.3642. Min Act: -0.0001

Data Index: 1829419 (The Pile)

Max Activating Token Index: 910

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.4695. Min Range: -0.4695

Max Act: 0.3175. Min Act: -0.0001

Data Index: 1281681 (The Pile)

Max Activating Token Index: 822

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.4695. Min Range: -0.4695

Max Act: 0.3039. Min Act: -0.0001

Data Index: 197114 (The Pile)

Max Activating Token Index: 965

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.4695. Min Range: -0.4695

Max Act: 0.3483. Min Act: -0.0001

Data Index: 776076 (The Pile)

Max Activating Token Index: 37

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.4695. Min Range: -0.4695

Max Act: 0.3274. Min Act: -0.0001

Data Index: 1895506 (The Pile)

Max Activating Token Index: 983

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.4695. Min Range: -0.4695

Max Act: 0.3665. Min Act: -0.0001

Data Index: 944378 (The Pile)

Max Activating Token Index: 788

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.4695. Min Range: -0.4695

Max Act: 0.3468. Min Act: -0.0001

Data Index: 1916546 (The Pile)

Max Activating Token Index: 983

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.4695. Min Range: -0.4695

Max Act: 0.3353. Min Act: -0.0001

Data Index: 1371762 (The Pile)

Max Activating Token Index: 801

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.4695. Min Range: -0.4695

Max Act: 0.3127. Min Act: -0.0001

Data Index: 602581 (The Pile)

Max Activating Token Index: 28

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.4695. Min Range: -0.4695

Max Act: 0.3321. Min Act: -0.0001

Data Index: 1656472 (The Pile)

Max Activating Token Index: 740

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.4695. Min Range: -0.4695

Max Act: 0.3432. Min Act: -0.0001

Data Index: 1173220 (The Pile)

Max Activating Token Index: 1001

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.4695. Min Range: -0.4695

Max Act: 0.3328. Min Act: -0.0001

Data Index: 1900216 (The Pile)

Max Activating Token Index: 911

Click toggle to see full text

Truncated

Full Text #19