< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 11 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 0.6037. Min Range: -0.6037

Max Act: 0.5858. Min Act: -0.0001

Data Index: 895883 (The Pile)

Max Activating Token Index: 114

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.6037. Min Range: -0.6037

Max Act: 0.5837. Min Act: -0.0001

Data Index: 1516060 (The Pile)

Max Activating Token Index: 385

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.6037. Min Range: -0.6037

Max Act: 0.5586. Min Act: -0.0001

Data Index: 342580 (The Pile)

Max Activating Token Index: 387

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.6037. Min Range: -0.6037

Max Act: 0.6037. Min Act: -0.0001

Data Index: 1248612 (The Pile)

Max Activating Token Index: 748

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.6037. Min Range: -0.6037

Max Act: 0.5178. Min Act: -0.0001

Data Index: 698217 (The Pile)

Max Activating Token Index: 644

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.6037. Min Range: -0.6037

Max Act: 0.5040. Min Act: -0.0001

Data Index: 1123348 (The Pile)

Max Activating Token Index: 432

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.6037. Min Range: -0.6037

Max Act: 0.5187. Min Act: -0.0001

Data Index: 361801 (The Pile)

Max Activating Token Index: 268

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.6037. Min Range: -0.6037

Max Act: 0.5111. Min Act: -0.0001

Data Index: 400673 (The Pile)

Max Activating Token Index: 888

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.6037. Min Range: -0.6037

Max Act: 0.4818. Min Act: -0.0001

Data Index: 1756021 (The Pile)

Max Activating Token Index: 796

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.6037. Min Range: -0.6037

Max Act: 0.3998. Min Act: -0.0001

Data Index: 138756 (The Pile)

Max Activating Token Index: 150

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.6037. Min Range: -0.6037

Max Act: 0.4437. Min Act: -0.0001

Data Index: 758233 (The Pile)

Max Activating Token Index: 722

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.6037. Min Range: -0.6037

Max Act: 0.4511. Min Act: -0.0001

Data Index: 1827295 (The Pile)

Max Activating Token Index: 215

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.6037. Min Range: -0.6037

Max Act: 0.4217. Min Act: -0.0001

Data Index: 71852 (The Pile)

Max Activating Token Index: 423

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.6037. Min Range: -0.6037

Max Act: 0.4159. Min Act: -0.0001

Data Index: 564504 (The Pile)

Max Activating Token Index: 36

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.6037. Min Range: -0.6037

Max Act: 0.4114. Min Act: -0.0001

Data Index: 171758 (The Pile)

Max Activating Token Index: 342

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.6037. Min Range: -0.6037

Max Act: 0.4353. Min Act: -0.0001

Data Index: 37282 (The Pile)

Max Activating Token Index: 216

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.6037. Min Range: -0.6037

Max Act: 0.4074. Min Act: -0.0001

Data Index: 919427 (The Pile)

Max Activating Token Index: 437

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.6037. Min Range: -0.6037

Max Act: 0.3910. Min Act: -0.0001

Data Index: 1921564 (The Pile)

Max Activating Token Index: 617

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.6037. Min Range: -0.6037

Max Act: 0.4152. Min Act: -0.0001

Data Index: 1628450 (The Pile)

Max Activating Token Index: 354

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.6037. Min Range: -0.6037

Max Act: 0.4118. Min Act: -0.0001

Data Index: 738187 (The Pile)

Max Activating Token Index: 449

Click toggle to see full text

Truncated

Full Text #19