< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 4030 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: 1.0587. Min Range: -1.0587

Max Act: 0.8966. Min Act: -0.0001

Data Index: 1790707 (The Pile)

Max Activating Token Index: 227

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 1.0587. Min Range: -1.0587

Max Act: 0.9328. Min Act: -0.0001

Data Index: 1006268 (The Pile)

Max Activating Token Index: 84

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 1.0587. Min Range: -1.0587

Max Act: 0.8726. Min Act: -0.0001

Data Index: 1335418 (The Pile)

Max Activating Token Index: 160

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 1.0587. Min Range: -1.0587

Max Act: 1.0587. Min Act: -0.0001

Data Index: 1727982 (The Pile)

Max Activating Token Index: 319

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 1.0587. Min Range: -1.0587

Max Act: 0.8978. Min Act: -0.0001

Data Index: 1988319 (The Pile)

Max Activating Token Index: 150

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 1.0587. Min Range: -1.0587

Max Act: 0.9320. Min Act: -0.0001

Data Index: 865852 (The Pile)

Max Activating Token Index: 275

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 1.0587. Min Range: -1.0587

Max Act: 0.9414. Min Act: -0.0001

Data Index: 1710555 (The Pile)

Max Activating Token Index: 283

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 1.0587. Min Range: -1.0587

Max Act: 0.9471. Min Act: -0.0001

Data Index: 1668070 (The Pile)

Max Activating Token Index: 39

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 1.0587. Min Range: -1.0587

Max Act: 0.8842. Min Act: -0.0001

Data Index: 588601 (The Pile)

Max Activating Token Index: 142

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 1.0587. Min Range: -1.0587

Max Act: 0.9135. Min Act: -0.0001

Data Index: 235678 (The Pile)

Max Activating Token Index: 38

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 1.0587. Min Range: -1.0587

Max Act: 0.9401. Min Act: -0.0001

Data Index: 957189 (The Pile)

Max Activating Token Index: 498

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 1.0587. Min Range: -1.0587

Max Act: 0.9090. Min Act: -0.0001

Data Index: 22799 (The Pile)

Max Activating Token Index: 177

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 1.0587. Min Range: -1.0587

Max Act: 1.0220. Min Act: -0.0001

Data Index: 758928 (The Pile)

Max Activating Token Index: 648

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 1.0587. Min Range: -1.0587

Max Act: 0.9310. Min Act: -0.0001

Data Index: 318264 (The Pile)

Max Activating Token Index: 246

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 1.0587. Min Range: -1.0587

Max Act: 0.8792. Min Act: -0.0001

Data Index: 1778912 (The Pile)

Max Activating Token Index: 116

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 1.0587. Min Range: -1.0587

Max Act: 0.8701. Min Act: -0.0001

Data Index: 61032 (The Pile)

Max Activating Token Index: 446

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 1.0587. Min Range: -1.0587

Max Act: 0.9741. Min Act: -0.0001

Data Index: 545961 (The Pile)

Max Activating Token Index: 240

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 1.0587. Min Range: -1.0587

Max Act: 0.8128. Min Act: -0.0001

Data Index: 773152 (The Pile)

Max Activating Token Index: 634

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 1.0587. Min Range: -1.0587

Max Act: 0.8891. Min Act: -0.0001

Data Index: 682646 (The Pile)

Max Activating Token Index: 147

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 1.0587. Min Range: -1.0587

Max Act: 0.8130. Min Act: -0.0001

Data Index: 1953183 (The Pile)

Max Activating Token Index: 145

Click toggle to see full text

Truncated

Full Text #19