< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 35 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: 5.4649. Min Range: -5.4649

Max Act: 5.4649. Min Act: -0.0000

Data Index: 1271506 (The Pile)

Max Activating Token Index: 13

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 5.4649. Min Range: -5.4649

Max Act: 5.1036. Min Act: -0.0000

Data Index: 1983043 (The Pile)

Max Activating Token Index: 12

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 5.4649. Min Range: -5.4649

Max Act: 4.8469. Min Act: -0.0000

Data Index: 839944 (The Pile)

Max Activating Token Index: 33

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 5.4649. Min Range: -5.4649

Max Act: 4.9300. Min Act: -0.0000

Data Index: 86016 (The Pile)

Max Activating Token Index: 19

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 5.4649. Min Range: -5.4649

Max Act: 4.7133. Min Act: -0.0000

Data Index: 1630576 (The Pile)

Max Activating Token Index: 40

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 5.4649. Min Range: -5.4649

Max Act: 4.8412. Min Act: -0.0000

Data Index: 1985525 (The Pile)

Max Activating Token Index: 22

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 5.4649. Min Range: -5.4649

Max Act: 4.4185. Min Act: -0.0000

Data Index: 1005709 (The Pile)

Max Activating Token Index: 12

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 5.4649. Min Range: -5.4649

Max Act: 4.5813. Min Act: -0.0000

Data Index: 246039 (The Pile)

Max Activating Token Index: 85

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 5.4649. Min Range: -5.4649

Max Act: 4.5623. Min Act: -0.0000

Data Index: 1695331 (The Pile)

Max Activating Token Index: 988

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 5.4649. Min Range: -5.4649

Max Act: 4.4098. Min Act: -0.0000

Data Index: 380867 (The Pile)

Max Activating Token Index: 14

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 5.4649. Min Range: -5.4649

Max Act: 4.4118. Min Act: -0.0000

Data Index: 1532291 (The Pile)

Max Activating Token Index: 519

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 5.4649. Min Range: -5.4649

Max Act: 4.3715. Min Act: -0.0000

Data Index: 918011 (The Pile)

Max Activating Token Index: 64

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 5.4649. Min Range: -5.4649

Max Act: 4.5446. Min Act: -0.0000

Data Index: 268657 (The Pile)

Max Activating Token Index: 534

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 5.4649. Min Range: -5.4649

Max Act: 4.3489. Min Act: -0.0000

Data Index: 618451 (The Pile)

Max Activating Token Index: 159

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 5.4649. Min Range: -5.4649

Max Act: 4.4985. Min Act: -0.0000

Data Index: 955398 (The Pile)

Max Activating Token Index: 35

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 5.4649. Min Range: -5.4649

Max Act: 4.4688. Min Act: -0.0000

Data Index: 498865 (The Pile)

Max Activating Token Index: 667

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 5.4649. Min Range: -5.4649

Max Act: 4.4997. Min Act: -0.0000

Data Index: 663353 (The Pile)

Max Activating Token Index: 7

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 5.4649. Min Range: -5.4649

Max Act: 4.4408. Min Act: -0.0000

Data Index: 637145 (The Pile)

Max Activating Token Index: 44

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 5.4649. Min Range: -5.4649

Max Act: 4.4222. Min Act: -0.0000

Data Index: 1623200 (The Pile)

Max Activating Token Index: 482

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 5.4649. Min Range: -5.4649

Max Act: 4.2603. Min Act: -0.0000

Data Index: 1329716 (The Pile)

Max Activating Token Index: 276

Click toggle to see full text

Truncated

Full Text #19