< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 28 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0679. Min Act: -0.0003

Data Index: 755895 (The Pile)

Max Activating Token Index: 277

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0625. Min Act: -0.0003

Data Index: 1965883 (The Pile)

Max Activating Token Index: 771

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0603. Min Act: -0.0003

Data Index: 793399 (The Pile)

Max Activating Token Index: 954

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0572. Min Act: -0.0003

Data Index: 1002277 (The Pile)

Max Activating Token Index: 817

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0599. Min Act: -0.0003

Data Index: 631060 (The Pile)

Max Activating Token Index: 535

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0585. Min Act: -0.0003

Data Index: 1573098 (The Pile)

Max Activating Token Index: 554

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0595. Min Act: -0.0003

Data Index: 1944327 (The Pile)

Max Activating Token Index: 32

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0576. Min Act: -0.0003

Data Index: 592925 (The Pile)

Max Activating Token Index: 510

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0575. Min Act: -0.0003

Data Index: 716590 (The Pile)

Max Activating Token Index: 140

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0574. Min Act: -0.0003

Data Index: 1958205 (The Pile)

Max Activating Token Index: 697

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0550. Min Act: -0.0003

Data Index: 296283 (The Pile)

Max Activating Token Index: 429

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0537. Min Act: -0.0003

Data Index: 13104 (The Pile)

Max Activating Token Index: 229

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0560. Min Act: -0.0003

Data Index: 1082754 (The Pile)

Max Activating Token Index: 158

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0556. Min Act: -0.0003

Data Index: 1722853 (The Pile)

Max Activating Token Index: 84

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0555. Min Act: -0.0003

Data Index: 985932 (The Pile)

Max Activating Token Index: 996

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0539. Min Act: -0.0003

Data Index: 907766 (The Pile)

Max Activating Token Index: 110

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0557. Min Act: -0.0003

Data Index: 1787259 (The Pile)

Max Activating Token Index: 48

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0548. Min Act: -0.0003

Data Index: 1475081 (The Pile)

Max Activating Token Index: 744

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0523. Min Act: -0.0003

Data Index: 867246 (The Pile)

Max Activating Token Index: 477

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0565. Min Act: -0.0003

Data Index: 316101 (The Pile)

Max Activating Token Index: 542

Click toggle to see full text

Truncated

Full Text #19