< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 18 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 0.0680. Min Range: -0.0680

Max Act: 0.0680. Min Act: 0.0000

Data Index: 1062927 (The Pile)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.0680. Min Range: -0.0680

Max Act: 0.0508. Min Act: 0.0000

Data Index: 340913 (The Pile)

Max Activating Token Index: 356

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.0680. Min Range: -0.0680

Max Act: 0.0516. Min Act: -0.0000

Data Index: 1156557 (The Pile)

Max Activating Token Index: 848

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.0680. Min Range: -0.0680

Max Act: 0.0505. Min Act: -0.0000

Data Index: 1659599 (The Pile)

Max Activating Token Index: 72

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.0680. Min Range: -0.0680

Max Act: 0.0506. Min Act: -0.0000

Data Index: 1668601 (The Pile)

Max Activating Token Index: 521

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.0680. Min Range: -0.0680

Max Act: 0.0503. Min Act: 0.0000

Data Index: 1945886 (The Pile)

Max Activating Token Index: 73

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.0680. Min Range: -0.0680

Max Act: 0.0496. Min Act: 0.0000

Data Index: 1224054 (The Pile)

Max Activating Token Index: 990

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.0680. Min Range: -0.0680

Max Act: 0.0498. Min Act: -0.0000

Data Index: 1039009 (The Pile)

Max Activating Token Index: 86

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.0680. Min Range: -0.0680

Max Act: 0.0486. Min Act: 0.0000

Data Index: 1918795 (The Pile)

Max Activating Token Index: 862

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.0680. Min Range: -0.0680

Max Act: 0.0482. Min Act: -0.0000

Data Index: 866202 (The Pile)

Max Activating Token Index: 841

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.0680. Min Range: -0.0680

Max Act: 0.0481. Min Act: 0.0000

Data Index: 1894925 (The Pile)

Max Activating Token Index: 1016

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.0680. Min Range: -0.0680

Max Act: 0.0481. Min Act: 0.0000

Data Index: 1337055 (The Pile)

Max Activating Token Index: 470

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.0680. Min Range: -0.0680

Max Act: 0.0480. Min Act: -0.0000

Data Index: 1575703 (The Pile)

Max Activating Token Index: 176

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.0680. Min Range: -0.0680

Max Act: 0.0477. Min Act: 0.0000

Data Index: 684934 (The Pile)

Max Activating Token Index: 889

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.0680. Min Range: -0.0680

Max Act: 0.0478. Min Act: -0.0000

Data Index: 29148 (The Pile)

Max Activating Token Index: 158

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.0680. Min Range: -0.0680

Max Act: 0.0477. Min Act: 0.0000

Data Index: 96497 (The Pile)

Max Activating Token Index: 117

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.0680. Min Range: -0.0680

Max Act: 0.0476. Min Act: -0.0000

Data Index: 996511 (The Pile)

Max Activating Token Index: 507

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.0680. Min Range: -0.0680

Max Act: 0.0474. Min Act: -0.0000

Data Index: 504167 (The Pile)

Max Activating Token Index: 477

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.0680. Min Range: -0.0680

Max Act: 0.0474. Min Act: 0.0000

Data Index: 25666 (The Pile)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.0680. Min Range: -0.0680

Max Act: 0.0456. Min Act: -0.0000

Data Index: 74040 (The Pile)

Max Activating Token Index: 845

Click toggle to see full text

Truncated

Full Text #19