< Prev | Home | Model | Random | Next >

Model: SoLU Model: 2 Layers, 2944 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-2l-pile')



Text #0

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0835. Min Act: -0.0002

Data Index: 1999835 (The Pile)

Max Activating Token Index: 474

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0721. Min Act: -0.0002

Data Index: 267340 (The Pile)

Max Activating Token Index: 718

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0597. Min Act: -0.0002

Data Index: 480544 (The Pile)

Max Activating Token Index: 684

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0677. Min Act: -0.0002

Data Index: 1437609 (The Pile)

Max Activating Token Index: 824

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0662. Min Act: -0.0002

Data Index: 1602078 (The Pile)

Max Activating Token Index: 143

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0675. Min Act: -0.0002

Data Index: 1035477 (The Pile)

Max Activating Token Index: 209

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0625. Min Act: -0.0002

Data Index: 925937 (The Pile)

Max Activating Token Index: 718

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0603. Min Act: -0.0002

Data Index: 1431574 (The Pile)

Max Activating Token Index: 847

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0615. Min Act: -0.0002

Data Index: 1031249 (The Pile)

Max Activating Token Index: 269

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0667. Min Act: -0.0002

Data Index: 428641 (The Pile)

Max Activating Token Index: 800

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0646. Min Act: -0.0002

Data Index: 290596 (The Pile)

Max Activating Token Index: 148

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0613. Min Act: -0.0002

Data Index: 1739930 (The Pile)

Max Activating Token Index: 878

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0586. Min Act: -0.0002

Data Index: 46307 (The Pile)

Max Activating Token Index: 349

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0561. Min Act: -0.0002

Data Index: 517631 (The Pile)

Max Activating Token Index: 500

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0622. Min Act: -0.0002

Data Index: 1198530 (The Pile)

Max Activating Token Index: 283

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0583. Min Act: -0.0002

Data Index: 1944381 (The Pile)

Max Activating Token Index: 529

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0548. Min Act: -0.0002

Data Index: 662286 (The Pile)

Max Activating Token Index: 53

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0629. Min Act: -0.0002

Data Index: 215974 (The Pile)

Max Activating Token Index: 210

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0574. Min Act: -0.0002

Data Index: 831136 (The Pile)

Max Activating Token Index: 343

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0585. Min Act: -0.0002

Data Index: 1992040 (The Pile)

Max Activating Token Index: 670

Click toggle to see full text

Truncated

Full Text #19