< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 2019 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 0.3725. Min Range: -0.3725

Max Act: 0.3725. Min Act: -0.0001

Data Index: 2133 (The Pile)

Max Activating Token Index: 636

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.3725. Min Range: -0.3725

Max Act: 0.3531. Min Act: -0.0001

Data Index: 510341 (The Pile)

Max Activating Token Index: 20

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.3725. Min Range: -0.3725

Max Act: 0.3434. Min Act: -0.0001

Data Index: 1271715 (The Pile)

Max Activating Token Index: 149

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.3725. Min Range: -0.3725

Max Act: 0.3359. Min Act: -0.0001

Data Index: 659049 (The Pile)

Max Activating Token Index: 452

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.3725. Min Range: -0.3725

Max Act: 0.3337. Min Act: -0.0001

Data Index: 1526223 (The Pile)

Max Activating Token Index: 284

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.3725. Min Range: -0.3725

Max Act: 0.3264. Min Act: -0.0001

Data Index: 1296278 (The Pile)

Max Activating Token Index: 901

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.3725. Min Range: -0.3725

Max Act: 0.3310. Min Act: -0.0001

Data Index: 521092 (The Pile)

Max Activating Token Index: 83

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.3725. Min Range: -0.3725

Max Act: 0.3196. Min Act: -0.0001

Data Index: 12617 (The Pile)

Max Activating Token Index: 676

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.3725. Min Range: -0.3725

Max Act: 0.3060. Min Act: -0.0001

Data Index: 390248 (The Pile)

Max Activating Token Index: 653

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.3725. Min Range: -0.3725

Max Act: 0.2934. Min Act: -0.0001

Data Index: 250047 (The Pile)

Max Activating Token Index: 956

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.3725. Min Range: -0.3725

Max Act: 0.3010. Min Act: -0.0001

Data Index: 1626672 (The Pile)

Max Activating Token Index: 152

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.3725. Min Range: -0.3725

Max Act: 0.3042. Min Act: -0.0001

Data Index: 629717 (The Pile)

Max Activating Token Index: 785

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.3725. Min Range: -0.3725

Max Act: 0.2896. Min Act: -0.0001

Data Index: 628773 (The Pile)

Max Activating Token Index: 122

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.3725. Min Range: -0.3725

Max Act: 0.2888. Min Act: -0.0001

Data Index: 301361 (The Pile)

Max Activating Token Index: 735

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.3725. Min Range: -0.3725

Max Act: 0.2989. Min Act: -0.0001

Data Index: 1519479 (The Pile)

Max Activating Token Index: 28

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.3725. Min Range: -0.3725

Max Act: 0.2764. Min Act: -0.0001

Data Index: 836103 (The Pile)

Max Activating Token Index: 857

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.3725. Min Range: -0.3725

Max Act: 0.2887. Min Act: -0.0001

Data Index: 1093364 (The Pile)

Max Activating Token Index: 351

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.3725. Min Range: -0.3725

Max Act: 0.2747. Min Act: -0.0001

Data Index: 796553 (The Pile)

Max Activating Token Index: 530

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.3725. Min Range: -0.3725

Max Act: 0.2642. Min Act: -0.0001

Data Index: 1006862 (The Pile)

Max Activating Token Index: 52

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.3725. Min Range: -0.3725

Max Act: 0.2712. Min Act: -0.0001

Data Index: 873804 (The Pile)

Max Activating Token Index: 629

Click toggle to see full text

Truncated

Full Text #19