< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 5072 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 1.8901. Min Range: -1.8901

Max Act: 1.8901. Min Act: -0.0000

Data Index: 698283 (The Pile)

Max Activating Token Index: 999

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 1.8901. Min Range: -1.8901

Max Act: 1.5442. Min Act: -0.0000

Data Index: 1724763 (The Pile)

Max Activating Token Index: 507

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 1.8901. Min Range: -1.8901

Max Act: 1.4378. Min Act: 0.0001

Data Index: 192513 (The Pile)

Max Activating Token Index: 274

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 1.8901. Min Range: -1.8901

Max Act: 1.3458. Min Act: -0.0000

Data Index: 704809 (The Pile)

Max Activating Token Index: 909

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 1.8901. Min Range: -1.8901

Max Act: 1.3155. Min Act: 0.0000

Data Index: 803592 (The Pile)

Max Activating Token Index: 80

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 1.8901. Min Range: -1.8901

Max Act: 1.4118. Min Act: 0.0000

Data Index: 719002 (The Pile)

Max Activating Token Index: 366

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 1.8901. Min Range: -1.8901

Max Act: 1.3255. Min Act: -0.0000

Data Index: 1410952 (The Pile)

Max Activating Token Index: 308

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 1.8901. Min Range: -1.8901

Max Act: 1.3877. Min Act: -0.0000

Data Index: 1152311 (The Pile)

Max Activating Token Index: 912

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 1.8901. Min Range: -1.8901

Max Act: 1.3030. Min Act: 0.0001

Data Index: 598927 (The Pile)

Max Activating Token Index: 1009

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 1.8901. Min Range: -1.8901

Max Act: 1.2160. Min Act: 0.0001

Data Index: 819450 (The Pile)

Max Activating Token Index: 693

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 1.8901. Min Range: -1.8901

Max Act: 1.3364. Min Act: -0.0000

Data Index: 868069 (The Pile)

Max Activating Token Index: 863

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 1.8901. Min Range: -1.8901

Max Act: 1.2671. Min Act: 0.0001

Data Index: 993280 (The Pile)

Max Activating Token Index: 145

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 1.8901. Min Range: -1.8901

Max Act: 1.2324. Min Act: -0.0000

Data Index: 196715 (The Pile)

Max Activating Token Index: 971

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 1.8901. Min Range: -1.8901

Max Act: 1.1373. Min Act: 0.0000

Data Index: 298334 (The Pile)

Max Activating Token Index: 506

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 1.8901. Min Range: -1.8901

Max Act: 1.1545. Min Act: -0.0000

Data Index: 1240835 (The Pile)

Max Activating Token Index: 627

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 1.8901. Min Range: -1.8901

Max Act: 1.1502. Min Act: -0.0000

Data Index: 855883 (The Pile)

Max Activating Token Index: 96

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 1.8901. Min Range: -1.8901

Max Act: 1.1222. Min Act: -0.0000

Data Index: 872517 (The Pile)

Max Activating Token Index: 752

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 1.8901. Min Range: -1.8901

Max Act: 1.0770. Min Act: -0.0000

Data Index: 1707610 (The Pile)

Max Activating Token Index: 582

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 1.8901. Min Range: -1.8901

Max Act: 1.0759. Min Act: -0.0000

Data Index: 1726102 (The Pile)

Max Activating Token Index: 956

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 1.8901. Min Range: -1.8901

Max Act: 1.0951. Min Act: -0.0000

Data Index: 1823763 (The Pile)

Max Activating Token Index: 362

Click toggle to see full text

Truncated

Full Text #19