< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 3022 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 0.3553. Min Range: -0.3553

Max Act: 0.3553. Min Act: -0.0001

Data Index: 1370324 (The Pile)

Max Activating Token Index: 36

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.3553. Min Range: -0.3553

Max Act: 0.3207. Min Act: -0.0001

Data Index: 273841 (The Pile)

Max Activating Token Index: 587

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.3553. Min Range: -0.3553

Max Act: 0.3154. Min Act: -0.0001

Data Index: 145342 (The Pile)

Max Activating Token Index: 184

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.3553. Min Range: -0.3553

Max Act: 0.3012. Min Act: -0.0001

Data Index: 825372 (The Pile)

Max Activating Token Index: 476

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.3553. Min Range: -0.3553

Max Act: 0.2896. Min Act: -0.0001

Data Index: 1559714 (The Pile)

Max Activating Token Index: 841

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.3553. Min Range: -0.3553

Max Act: 0.2643. Min Act: -0.0001

Data Index: 1874720 (The Pile)

Max Activating Token Index: 1002

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.3553. Min Range: -0.3553

Max Act: 0.3019. Min Act: -0.0001

Data Index: 1938149 (The Pile)

Max Activating Token Index: 172

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.3553. Min Range: -0.3553

Max Act: 0.2823. Min Act: -0.0001

Data Index: 324133 (The Pile)

Max Activating Token Index: 257

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.3553. Min Range: -0.3553

Max Act: 0.2840. Min Act: -0.0001

Data Index: 686510 (The Pile)

Max Activating Token Index: 896

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.3553. Min Range: -0.3553

Max Act: 0.2675. Min Act: -0.0001

Data Index: 40075 (The Pile)

Max Activating Token Index: 558

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.3553. Min Range: -0.3553

Max Act: 0.2859. Min Act: -0.0001

Data Index: 435798 (The Pile)

Max Activating Token Index: 344

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.3553. Min Range: -0.3553

Max Act: 0.2854. Min Act: -0.0001

Data Index: 557461 (The Pile)

Max Activating Token Index: 255

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.3553. Min Range: -0.3553

Max Act: 0.2736. Min Act: -0.0001

Data Index: 1134679 (The Pile)

Max Activating Token Index: 352

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.3553. Min Range: -0.3553

Max Act: 0.2827. Min Act: -0.0001

Data Index: 825241 (The Pile)

Max Activating Token Index: 584

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.3553. Min Range: -0.3553

Max Act: 0.2632. Min Act: -0.0001

Data Index: 544454 (The Pile)

Max Activating Token Index: 118

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.3553. Min Range: -0.3553

Max Act: 0.2694. Min Act: -0.0001

Data Index: 1312292 (The Pile)

Max Activating Token Index: 517

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.3553. Min Range: -0.3553

Max Act: 0.2883. Min Act: -0.0001

Data Index: 1694890 (The Pile)

Max Activating Token Index: 771

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.3553. Min Range: -0.3553

Max Act: 0.2883. Min Act: -0.0001

Data Index: 3003 (The Pile)

Max Activating Token Index: 417

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.3553. Min Range: -0.3553

Max Act: 0.2676. Min Act: -0.0001

Data Index: 800369 (The Pile)

Max Activating Token Index: 240

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.3553. Min Range: -0.3553

Max Act: 0.2767. Min Act: -0.0001

Data Index: 572674 (The Pile)

Max Activating Token Index: 467

Click toggle to see full text

Truncated

Full Text #19