< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 54 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 2.3950. Min Range: -2.3950

Max Act: 2.1669. Min Act: -0.0000

Data Index: 582824 (The Pile)

Max Activating Token Index: 749

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 2.3950. Min Range: -2.3950

Max Act: 2.3950. Min Act: -0.0000

Data Index: 1224173 (The Pile)

Max Activating Token Index: 528

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 2.3950. Min Range: -2.3950

Max Act: 2.1168. Min Act: -0.0000

Data Index: 1726587 (The Pile)

Max Activating Token Index: 341

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 2.3950. Min Range: -2.3950

Max Act: 2.0896. Min Act: 0.0000

Data Index: 435391 (The Pile)

Max Activating Token Index: 289

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 2.3950. Min Range: -2.3950

Max Act: 1.8404. Min Act: -0.0000

Data Index: 1430427 (The Pile)

Max Activating Token Index: 676

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 2.3950. Min Range: -2.3950

Max Act: 1.9712. Min Act: -0.0000

Data Index: 211294 (The Pile)

Max Activating Token Index: 955

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 2.3950. Min Range: -2.3950

Max Act: 1.7958. Min Act: -0.0000

Data Index: 1966662 (The Pile)

Max Activating Token Index: 732

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 2.3950. Min Range: -2.3950

Max Act: 1.8171. Min Act: -0.0000

Data Index: 426294 (The Pile)

Max Activating Token Index: 268

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 2.3950. Min Range: -2.3950

Max Act: 2.0016. Min Act: -0.0000

Data Index: 396518 (The Pile)

Max Activating Token Index: 699

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 2.3950. Min Range: -2.3950

Max Act: 1.8689. Min Act: -0.0000

Data Index: 44142 (The Pile)

Max Activating Token Index: 1006

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 2.3950. Min Range: -2.3950

Max Act: 1.9395. Min Act: -0.0000

Data Index: 1351668 (The Pile)

Max Activating Token Index: 923

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 2.3950. Min Range: -2.3950

Max Act: 1.9201. Min Act: 0.0000

Data Index: 633884 (The Pile)

Max Activating Token Index: 522

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 2.3950. Min Range: -2.3950

Max Act: 1.5935. Min Act: 0.0000

Data Index: 1616654 (The Pile)

Max Activating Token Index: 851

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 2.3950. Min Range: -2.3950

Max Act: 1.6902. Min Act: -0.0000

Data Index: 594409 (The Pile)

Max Activating Token Index: 987

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 2.3950. Min Range: -2.3950

Max Act: 1.5689. Min Act: -0.0000

Data Index: 393748 (The Pile)

Max Activating Token Index: 253

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 2.3950. Min Range: -2.3950

Max Act: 1.6645. Min Act: -0.0000

Data Index: 1639825 (The Pile)

Max Activating Token Index: 813

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 2.3950. Min Range: -2.3950

Max Act: 1.7512. Min Act: -0.0000

Data Index: 1262432 (The Pile)

Max Activating Token Index: 837

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 2.3950. Min Range: -2.3950

Max Act: 1.6703. Min Act: -0.0000

Data Index: 1972846 (The Pile)

Max Activating Token Index: 357

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 2.3950. Min Range: -2.3950

Max Act: 1.6692. Min Act: -0.0000

Data Index: 318204 (The Pile)

Max Activating Token Index: 137

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 2.3950. Min Range: -2.3950

Max Act: 1.6416. Min Act: 0.0000

Data Index: 1030054 (The Pile)

Max Activating Token Index: 487

Click toggle to see full text

Truncated

Full Text #19