< Prev | Home | Model | Random | Next >

Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 41 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')



Text #0

Max Range: 0.1112. Min Range: -0.1112

Max Act: 0.1112. Min Act: -0.0001

Data Index: 1180990 (The Pile)

Max Activating Token Index: 974

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.1112. Min Range: -0.1112

Max Act: 0.0795. Min Act: -0.0002

Data Index: 666623 (The Pile)

Max Activating Token Index: 839

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.1112. Min Range: -0.1112

Max Act: 0.0662. Min Act: -0.0002

Data Index: 373914 (The Pile)

Max Activating Token Index: 116

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.1112. Min Range: -0.1112

Max Act: 0.0671. Min Act: -0.0002

Data Index: 1916005 (The Pile)

Max Activating Token Index: 127

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.1112. Min Range: -0.1112

Max Act: 0.0621. Min Act: -0.0002

Data Index: 744070 (The Pile)

Max Activating Token Index: 755

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.1112. Min Range: -0.1112

Max Act: 0.0657. Min Act: -0.0002

Data Index: 1023594 (The Pile)

Max Activating Token Index: 352

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.1112. Min Range: -0.1112

Max Act: 0.0640. Min Act: -0.0002

Data Index: 278477 (The Pile)

Max Activating Token Index: 880

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.1112. Min Range: -0.1112

Max Act: 0.0590. Min Act: -0.0002

Data Index: 57693 (The Pile)

Max Activating Token Index: 42

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.1112. Min Range: -0.1112

Max Act: 0.0616. Min Act: -0.0002

Data Index: 1690941 (The Pile)

Max Activating Token Index: 592

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.1112. Min Range: -0.1112

Max Act: 0.0584. Min Act: -0.0002

Data Index: 1131763 (The Pile)

Max Activating Token Index: 478

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.1112. Min Range: -0.1112

Max Act: 0.0554. Min Act: -0.0002

Data Index: 1066875 (The Pile)

Max Activating Token Index: 41

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.1112. Min Range: -0.1112

Max Act: 0.0572. Min Act: -0.0002

Data Index: 1337600 (The Pile)

Max Activating Token Index: 820

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.1112. Min Range: -0.1112

Max Act: 0.0535. Min Act: -0.0002

Data Index: 1065106 (The Pile)

Max Activating Token Index: 274

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.1112. Min Range: -0.1112

Max Act: 0.0559. Min Act: -0.0002

Data Index: 1983713 (The Pile)

Max Activating Token Index: 1004

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.1112. Min Range: -0.1112

Max Act: 0.0622. Min Act: -0.0002

Data Index: 1064505 (The Pile)

Max Activating Token Index: 935

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.1112. Min Range: -0.1112

Max Act: 0.0458. Min Act: -0.0002

Data Index: 1934314 (The Pile)

Max Activating Token Index: 930

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.1112. Min Range: -0.1112

Max Act: 0.0510. Min Act: -0.0002

Data Index: 1699495 (The Pile)

Max Activating Token Index: 177

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.1112. Min Range: -0.1112

Max Act: 0.0538. Min Act: -0.0002

Data Index: 375991 (The Pile)

Max Activating Token Index: 490

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.1112. Min Range: -0.1112

Max Act: 0.0538. Min Act: -0.0002

Data Index: 1399877 (The Pile)

Max Activating Token Index: 560

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.1112. Min Range: -0.1112

Max Act: 0.0511. Min Act: -0.0002

Data Index: 1607397 (The Pile)

Max Activating Token Index: 265

Click toggle to see full text

Truncated

Full Text #19