< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 3064 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 0.7449. Min Range: -0.7449

Max Act: 0.7449. Min Act: -0.0001

Data Index: 287658 (The Pile)

Max Activating Token Index: 356

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.7449. Min Range: -0.7449

Max Act: 0.6675. Min Act: -0.0000

Data Index: 502520 (The Pile)

Max Activating Token Index: 430

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.7449. Min Range: -0.7449

Max Act: 0.6074. Min Act: -0.0001

Data Index: 159067 (The Pile)

Max Activating Token Index: 596

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.7449. Min Range: -0.7449

Max Act: 0.5470. Min Act: -0.0000

Data Index: 1648916 (The Pile)

Max Activating Token Index: 922

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.7449. Min Range: -0.7449

Max Act: 0.5353. Min Act: -0.0001

Data Index: 37796 (The Pile)

Max Activating Token Index: 906

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.7449. Min Range: -0.7449

Max Act: 0.5612. Min Act: -0.0001

Data Index: 153395 (The Pile)

Max Activating Token Index: 928

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.7449. Min Range: -0.7449

Max Act: 0.5400. Min Act: -0.0001

Data Index: 226380 (The Pile)

Max Activating Token Index: 812

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.7449. Min Range: -0.7449

Max Act: 0.5328. Min Act: -0.0001

Data Index: 1685667 (The Pile)

Max Activating Token Index: 991

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.7449. Min Range: -0.7449

Max Act: 0.5262. Min Act: -0.0001

Data Index: 1778489 (The Pile)

Max Activating Token Index: 878

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.7449. Min Range: -0.7449

Max Act: 0.4973. Min Act: -0.0001

Data Index: 20886 (The Pile)

Max Activating Token Index: 136

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.7449. Min Range: -0.7449

Max Act: 0.5189. Min Act: -0.0001

Data Index: 1931999 (The Pile)

Max Activating Token Index: 671

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.7449. Min Range: -0.7449

Max Act: 0.5227. Min Act: -0.0001

Data Index: 677152 (The Pile)

Max Activating Token Index: 237

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.7449. Min Range: -0.7449

Max Act: 0.5133. Min Act: -0.0001

Data Index: 852978 (The Pile)

Max Activating Token Index: 434

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.7449. Min Range: -0.7449

Max Act: 0.5098. Min Act: -0.0000

Data Index: 294243 (The Pile)

Max Activating Token Index: 506

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.7449. Min Range: -0.7449

Max Act: 0.5433. Min Act: -0.0001

Data Index: 1164718 (The Pile)

Max Activating Token Index: 205

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.7449. Min Range: -0.7449

Max Act: 0.5173. Min Act: -0.0000

Data Index: 724642 (The Pile)

Max Activating Token Index: 777

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.7449. Min Range: -0.7449

Max Act: 0.5054. Min Act: -0.0001

Data Index: 1837797 (The Pile)

Max Activating Token Index: 684

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.7449. Min Range: -0.7449

Max Act: 0.4842. Min Act: -0.0001

Data Index: 1076248 (The Pile)

Max Activating Token Index: 948

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.7449. Min Range: -0.7449

Max Act: 0.4744. Min Act: -0.0000

Data Index: 523235 (The Pile)

Max Activating Token Index: 314

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.7449. Min Range: -0.7449

Max Act: 0.4909. Min Act: -0.0001

Data Index: 1812220 (The Pile)

Max Activating Token Index: 78

Click toggle to see full text

Truncated

Full Text #19