< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 2 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 4.3242. Min Range: -4.3242

Max Act: 4.3242. Min Act: -0.0000

Data Index: 18921 (The Pile)

Max Activating Token Index: 356

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 4.3242. Min Range: -4.3242

Max Act: 3.9066. Min Act: -0.0000

Data Index: 534863 (The Pile)

Max Activating Token Index: 37

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 4.3242. Min Range: -4.3242

Max Act: 3.8665. Min Act: -0.0000

Data Index: 91445 (The Pile)

Max Activating Token Index: 722

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 4.3242. Min Range: -4.3242

Max Act: 4.1302. Min Act: -0.0000

Data Index: 243380 (The Pile)

Max Activating Token Index: 322

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 4.3242. Min Range: -4.3242

Max Act: 3.3519. Min Act: -0.0000

Data Index: 419887 (The Pile)

Max Activating Token Index: 588

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 4.3242. Min Range: -4.3242

Max Act: 3.5313. Min Act: -0.0000

Data Index: 932456 (The Pile)

Max Activating Token Index: 483

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 4.3242. Min Range: -4.3242

Max Act: 3.4099. Min Act: -0.0000

Data Index: 1529204 (The Pile)

Max Activating Token Index: 457

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 4.3242. Min Range: -4.3242

Max Act: 3.6217. Min Act: -0.0000

Data Index: 307016 (The Pile)

Max Activating Token Index: 712

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 4.3242. Min Range: -4.3242

Max Act: 3.5567. Min Act: -0.0000

Data Index: 602908 (The Pile)

Max Activating Token Index: 80

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 4.3242. Min Range: -4.3242

Max Act: 3.1593. Min Act: -0.0000

Data Index: 1329101 (The Pile)

Max Activating Token Index: 164

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 4.3242. Min Range: -4.3242

Max Act: 3.1924. Min Act: -0.0000

Data Index: 1036264 (The Pile)

Max Activating Token Index: 238

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 4.3242. Min Range: -4.3242

Max Act: 2.9225. Min Act: -0.0000

Data Index: 1988393 (The Pile)

Max Activating Token Index: 654

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 4.3242. Min Range: -4.3242

Max Act: 2.7463. Min Act: -0.0000

Data Index: 330437 (The Pile)

Max Activating Token Index: 430

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 4.3242. Min Range: -4.3242

Max Act: 3.1583. Min Act: -0.0000

Data Index: 1248569 (The Pile)

Max Activating Token Index: 218

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 4.3242. Min Range: -4.3242

Max Act: 3.1108. Min Act: -0.0000

Data Index: 1587285 (The Pile)

Max Activating Token Index: 807

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 4.3242. Min Range: -4.3242

Max Act: 3.1567. Min Act: -0.0000

Data Index: 1548206 (The Pile)

Max Activating Token Index: 68

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 4.3242. Min Range: -4.3242

Max Act: 3.1204. Min Act: -0.0000

Data Index: 1660819 (The Pile)

Max Activating Token Index: 504

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 4.3242. Min Range: -4.3242

Max Act: 2.9400. Min Act: -0.0000

Data Index: 1084405 (The Pile)

Max Activating Token Index: 57

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 4.3242. Min Range: -4.3242

Max Act: 3.3662. Min Act: -0.0000

Data Index: 254457 (The Pile)

Max Activating Token Index: 717

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 4.3242. Min Range: -4.3242

Max Act: 2.8292. Min Act: -0.0000

Data Index: 641454 (The Pile)

Max Activating Token Index: 914

Click toggle to see full text

Truncated

Full Text #19