< Prev | Home | Model | Random | Next >

Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 45 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')



Text #0

Max Range: 0.2928. Min Range: -0.2928

Max Act: 0.2928. Min Act: -0.0001

Data Index: 1739039 (The Pile)

Max Activating Token Index: 28

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.2928. Min Range: -0.2928

Max Act: 0.2700. Min Act: -0.0001

Data Index: 1920759 (The Pile)

Max Activating Token Index: 5

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.2928. Min Range: -0.2928

Max Act: 0.2804. Min Act: -0.0001

Data Index: 1616635 (The Pile)

Max Activating Token Index: 7

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.2928. Min Range: -0.2928

Max Act: 0.2786. Min Act: -0.0001

Data Index: 531152 (The Pile)

Max Activating Token Index: 14

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.2928. Min Range: -0.2928

Max Act: 0.2581. Min Act: -0.0001

Data Index: 1379079 (The Pile)

Max Activating Token Index: 10

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.2928. Min Range: -0.2928

Max Act: 0.2720. Min Act: -0.0001

Data Index: 811281 (The Pile)

Max Activating Token Index: 38

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.2928. Min Range: -0.2928

Max Act: 0.2535. Min Act: -0.0001

Data Index: 92718 (The Pile)

Max Activating Token Index: 17

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.2928. Min Range: -0.2928

Max Act: 0.2718. Min Act: -0.0001

Data Index: 173704 (The Pile)

Max Activating Token Index: 16

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.2928. Min Range: -0.2928

Max Act: 0.2683. Min Act: -0.0001

Data Index: 1024001 (The Pile)

Max Activating Token Index: 64

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.2928. Min Range: -0.2928

Max Act: 0.2672. Min Act: -0.0001

Data Index: 944383 (The Pile)

Max Activating Token Index: 45

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.2928. Min Range: -0.2928

Max Act: 0.2460. Min Act: -0.0001

Data Index: 487707 (The Pile)

Max Activating Token Index: 30

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.2928. Min Range: -0.2928

Max Act: 0.2826. Min Act: -0.0001

Data Index: 1351417 (The Pile)

Max Activating Token Index: 26

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.2928. Min Range: -0.2928

Max Act: 0.2638. Min Act: -0.0001

Data Index: 855842 (The Pile)

Max Activating Token Index: 10

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.2928. Min Range: -0.2928

Max Act: 0.2642. Min Act: -0.0001

Data Index: 1567636 (The Pile)

Max Activating Token Index: 17

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.2928. Min Range: -0.2928

Max Act: 0.2552. Min Act: -0.0001

Data Index: 1879712 (The Pile)

Max Activating Token Index: 28

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.2928. Min Range: -0.2928

Max Act: 0.2702. Min Act: -0.0001

Data Index: 299826 (The Pile)

Max Activating Token Index: 15

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.2928. Min Range: -0.2928

Max Act: 0.2381. Min Act: -0.0001

Data Index: 224426 (The Pile)

Max Activating Token Index: 272

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.2928. Min Range: -0.2928

Max Act: 0.2438. Min Act: -0.0001

Data Index: 995955 (The Pile)

Max Activating Token Index: 29

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.2928. Min Range: -0.2928

Max Act: 0.2490. Min Act: -0.0001

Data Index: 1685654 (The Pile)

Max Activating Token Index: 11

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.2928. Min Range: -0.2928

Max Act: 0.2588. Min Act: -0.0001

Data Index: 1685021 (The Pile)

Max Activating Token Index: 13

Click toggle to see full text

Truncated

Full Text #19