< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 5085 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 1.5222. Min Range: -1.5222

Max Act: 1.5190. Min Act: 0.0000

Data Index: 123496 (The Pile)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 1.5222. Min Range: -1.5222

Max Act: 1.5222. Min Act: 0.0001

Data Index: 474609 (The Pile)

Max Activating Token Index: 774

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 1.5222. Min Range: -1.5222

Max Act: 1.3085. Min Act: 0.0000

Data Index: 310899 (The Pile)

Max Activating Token Index: 358

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 1.5222. Min Range: -1.5222

Max Act: 1.2915. Min Act: 0.0000

Data Index: 270506 (The Pile)

Max Activating Token Index: 458

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 1.5222. Min Range: -1.5222

Max Act: 1.1713. Min Act: 0.0000

Data Index: 1184964 (The Pile)

Max Activating Token Index: 87

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 1.5222. Min Range: -1.5222

Max Act: 1.2314. Min Act: 0.0001

Data Index: 1204863 (The Pile)

Max Activating Token Index: 856

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 1.5222. Min Range: -1.5222

Max Act: 1.2187. Min Act: 0.0001

Data Index: 793679 (The Pile)

Max Activating Token Index: 213

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 1.5222. Min Range: -1.5222

Max Act: 1.2823. Min Act: -0.0000

Data Index: 350160 (The Pile)

Max Activating Token Index: 111

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 1.5222. Min Range: -1.5222

Max Act: 1.2043. Min Act: 0.0001

Data Index: 1540468 (The Pile)

Max Activating Token Index: 764

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 1.5222. Min Range: -1.5222

Max Act: 1.1950. Min Act: -0.0000

Data Index: 1255179 (The Pile)

Max Activating Token Index: 410

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 1.5222. Min Range: -1.5222

Max Act: 1.2401. Min Act: 0.0000

Data Index: 1261049 (The Pile)

Max Activating Token Index: 314

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 1.5222. Min Range: -1.5222

Max Act: 1.1706. Min Act: -0.0000

Data Index: 883480 (The Pile)

Max Activating Token Index: 188

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 1.5222. Min Range: -1.5222

Max Act: 1.0853. Min Act: 0.0001

Data Index: 261509 (The Pile)

Max Activating Token Index: 113

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 1.5222. Min Range: -1.5222

Max Act: 1.1394. Min Act: 0.0000

Data Index: 1131585 (The Pile)

Max Activating Token Index: 306

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 1.5222. Min Range: -1.5222

Max Act: 1.1991. Min Act: 0.0002

Data Index: 794433 (The Pile)

Max Activating Token Index: 139

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 1.5222. Min Range: -1.5222

Max Act: 1.1837. Min Act: 0.0000

Data Index: 995076 (The Pile)

Max Activating Token Index: 561

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 1.5222. Min Range: -1.5222

Max Act: 1.1865. Min Act: 0.0001

Data Index: 683811 (The Pile)

Max Activating Token Index: 636

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 1.5222. Min Range: -1.5222

Max Act: 1.1023. Min Act: 0.0002

Data Index: 443181 (The Pile)

Max Activating Token Index: 160

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 1.5222. Min Range: -1.5222

Max Act: 1.0938. Min Act: 0.0001

Data Index: 1753639 (The Pile)

Max Activating Token Index: 871

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 1.5222. Min Range: -1.5222

Max Act: 1.0794. Min Act: 0.0000

Data Index: 1907591 (The Pile)

Max Activating Token Index: 345

Click toggle to see full text

Truncated

Full Text #19