< Prev | Home | Model | Random | Next >

Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

Dataset: The Pile

Neuron 29 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l-pile')



Text #0

Max Range: 0.4985. Min Range: -0.4985

Max Act: 0.4985. Min Act: -0.0001

Data Index: 1932597 (The Pile)

Max Activating Token Index: 489

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.4985. Min Range: -0.4985

Max Act: 0.4642. Min Act: -0.0001

Data Index: 452309 (The Pile)

Max Activating Token Index: 467

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.4985. Min Range: -0.4985

Max Act: 0.4683. Min Act: -0.0001

Data Index: 538140 (The Pile)

Max Activating Token Index: 193

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.4985. Min Range: -0.4985

Max Act: 0.4201. Min Act: -0.0001

Data Index: 1432431 (The Pile)

Max Activating Token Index: 789

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.4985. Min Range: -0.4985

Max Act: 0.4191. Min Act: -0.0001

Data Index: 1706752 (The Pile)

Max Activating Token Index: 484

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.4985. Min Range: -0.4985

Max Act: 0.4152. Min Act: -0.0001

Data Index: 1657666 (The Pile)

Max Activating Token Index: 368

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.4985. Min Range: -0.4985

Max Act: 0.4297. Min Act: -0.0001

Data Index: 434374 (The Pile)

Max Activating Token Index: 603

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.4985. Min Range: -0.4985

Max Act: 0.4042. Min Act: -0.0001

Data Index: 1100878 (The Pile)

Max Activating Token Index: 151

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.4985. Min Range: -0.4985

Max Act: 0.3932. Min Act: -0.0001

Data Index: 449905 (The Pile)

Max Activating Token Index: 879

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.4985. Min Range: -0.4985

Max Act: 0.3980. Min Act: -0.0001

Data Index: 1626828 (The Pile)

Max Activating Token Index: 295

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.4985. Min Range: -0.4985

Max Act: 0.3981. Min Act: -0.0001

Data Index: 1744855 (The Pile)

Max Activating Token Index: 371

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.4985. Min Range: -0.4985

Max Act: 0.3868. Min Act: -0.0001

Data Index: 1559641 (The Pile)

Max Activating Token Index: 398

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.4985. Min Range: -0.4985

Max Act: 0.3864. Min Act: -0.0001

Data Index: 117794 (The Pile)

Max Activating Token Index: 730

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.4985. Min Range: -0.4985

Max Act: 0.3496. Min Act: -0.0001

Data Index: 771262 (The Pile)

Max Activating Token Index: 655

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.4985. Min Range: -0.4985

Max Act: 0.3834. Min Act: -0.0001

Data Index: 1324466 (The Pile)

Max Activating Token Index: 624

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.4985. Min Range: -0.4985

Max Act: 0.3703. Min Act: -0.0001

Data Index: 539563 (The Pile)

Max Activating Token Index: 782

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.4985. Min Range: -0.4985

Max Act: 0.3695. Min Act: -0.0001

Data Index: 1753779 (The Pile)

Max Activating Token Index: 389

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.4985. Min Range: -0.4985

Max Act: 0.3786. Min Act: -0.0001

Data Index: 832302 (The Pile)

Max Activating Token Index: 498

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.4985. Min Range: -0.4985

Max Act: 0.3668. Min Act: -0.0001

Data Index: 498484 (The Pile)

Max Activating Token Index: 982

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.4985. Min Range: -0.4985

Max Act: 0.3790. Min Act: -0.0001

Data Index: 1013389 (The Pile)

Max Activating Token Index: 470

Click toggle to see full text

Truncated

Full Text #19