< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 22 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: 0.0974. Min Range: -0.0974

Max Act: 0.0974. Min Act: -0.0001

Data Index: 430652 (The Pile)

Max Activating Token Index: 812

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0845. Min Act: -0.0001

Data Index: 699915 (The Pile)

Max Activating Token Index: 255

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0855. Min Act: -0.0001

Data Index: 1709033 (The Pile)

Max Activating Token Index: 894

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0799. Min Act: -0.0001

Data Index: 840705 (The Pile)

Max Activating Token Index: 585

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0757. Min Act: -0.0001

Data Index: 464742 (The Pile)

Max Activating Token Index: 850

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0726. Min Act: -0.0001

Data Index: 601025 (The Pile)

Max Activating Token Index: 358

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0701. Min Act: -0.0001

Data Index: 516715 (The Pile)

Max Activating Token Index: 119

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0718. Min Act: -0.0001

Data Index: 1980987 (The Pile)

Max Activating Token Index: 352

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0693. Min Act: -0.0001

Data Index: 1358431 (The Pile)

Max Activating Token Index: 686

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0689. Min Act: -0.0001

Data Index: 904546 (The Pile)

Max Activating Token Index: 761

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0665. Min Act: -0.0001

Data Index: 1294779 (The Pile)

Max Activating Token Index: 4

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0677. Min Act: -0.0001

Data Index: 134215 (The Pile)

Max Activating Token Index: 125

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0671. Min Act: -0.0001

Data Index: 1044418 (The Pile)

Max Activating Token Index: 120

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0641. Min Act: -0.0001

Data Index: 1700518 (The Pile)

Max Activating Token Index: 29

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0610. Min Act: -0.0001

Data Index: 1514845 (The Pile)

Max Activating Token Index: 288

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0634. Min Act: -0.0001

Data Index: 759397 (The Pile)

Max Activating Token Index: 621

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0663. Min Act: -0.0001

Data Index: 1851799 (The Pile)

Max Activating Token Index: 6

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0590. Min Act: -0.0001

Data Index: 1998376 (The Pile)

Max Activating Token Index: 164

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0585. Min Act: -0.0001

Data Index: 1746369 (The Pile)

Max Activating Token Index: 399

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0586. Min Act: -0.0001

Data Index: 974650 (The Pile)

Max Activating Token Index: 134

Click toggle to see full text

Truncated

Full Text #19