< Prev | Home | Model | Random | Next >

Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

Dataset: The Pile

Neuron 33 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l-pile')



Text #0

Max Range: 0.3695. Min Range: -0.3695

Max Act: 0.3695. Min Act: -0.0002

Data Index: 1404559 (The Pile)

Max Activating Token Index: 13

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.3695. Min Range: -0.3695

Max Act: 0.3403. Min Act: -0.0002

Data Index: 288497 (The Pile)

Max Activating Token Index: 13

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.3695. Min Range: -0.3695

Max Act: 0.3099. Min Act: -0.0002

Data Index: 177106 (The Pile)

Max Activating Token Index: 389

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.3695. Min Range: -0.3695

Max Act: 0.3157. Min Act: -0.0002

Data Index: 1237501 (The Pile)

Max Activating Token Index: 505

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.3695. Min Range: -0.3695

Max Act: 0.3037. Min Act: -0.0002

Data Index: 1855755 (The Pile)

Max Activating Token Index: 792

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.3695. Min Range: -0.3695

Max Act: 0.3135. Min Act: -0.0002

Data Index: 1782474 (The Pile)

Max Activating Token Index: 762

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.3695. Min Range: -0.3695

Max Act: 0.3448. Min Act: -0.0002

Data Index: 373236 (The Pile)

Max Activating Token Index: 685

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.3695. Min Range: -0.3695

Max Act: 0.3071. Min Act: -0.0002

Data Index: 1245470 (The Pile)

Max Activating Token Index: 24

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.3695. Min Range: -0.3695

Max Act: 0.3232. Min Act: -0.0002

Data Index: 829051 (The Pile)

Max Activating Token Index: 162

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.3695. Min Range: -0.3695

Max Act: 0.3102. Min Act: -0.0002

Data Index: 116252 (The Pile)

Max Activating Token Index: 9

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.3695. Min Range: -0.3695

Max Act: 0.3100. Min Act: -0.0002

Data Index: 143041 (The Pile)

Max Activating Token Index: 11

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.3695. Min Range: -0.3695

Max Act: 0.3085. Min Act: -0.0002

Data Index: 1090504 (The Pile)

Max Activating Token Index: 13

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.3695. Min Range: -0.3695

Max Act: 0.3087. Min Act: -0.0002

Data Index: 1483699 (The Pile)

Max Activating Token Index: 17

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.3695. Min Range: -0.3695

Max Act: 0.3077. Min Act: -0.0002

Data Index: 197765 (The Pile)

Max Activating Token Index: 6

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.3695. Min Range: -0.3695

Max Act: 0.3068. Min Act: -0.0002

Data Index: 473892 (The Pile)

Max Activating Token Index: 9

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.3695. Min Range: -0.3695

Max Act: 0.3064. Min Act: -0.0002

Data Index: 1492907 (The Pile)

Max Activating Token Index: 14

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.3695. Min Range: -0.3695

Max Act: 0.3049. Min Act: -0.0002

Data Index: 1749015 (The Pile)

Max Activating Token Index: 12

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.3695. Min Range: -0.3695

Max Act: 0.2886. Min Act: -0.0002

Data Index: 1442325 (The Pile)

Max Activating Token Index: 38

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.3695. Min Range: -0.3695

Max Act: 0.2995. Min Act: -0.0002

Data Index: 1109674 (The Pile)

Max Activating Token Index: 17

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.3695. Min Range: -0.3695

Max Act: 0.2859. Min Act: -0.0002

Data Index: 1351962 (The Pile)

Max Activating Token Index: 14

Click toggle to see full text

Truncated

Full Text #19