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

Dataset: The Pile

Neuron 3667 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6827. Min Range: -0.6827

Max Act: 0.6735. Min Act: -0.0000

Data Index: 1750121 (The Pile)

Max Activating Token Index: 897

Text #1

Max Range: 0.6827. Min Range: -0.6827

Max Act: 0.6266. Min Act: -0.0000

Data Index: 1936924 (The Pile)

Max Activating Token Index: 171

Text #2

Max Range: 0.6827. Min Range: -0.6827

Max Act: 0.6669. Min Act: -0.0000

Data Index: 386213 (The Pile)

Max Activating Token Index: 67

Text #3

Max Range: 0.6827. Min Range: -0.6827

Max Act: 0.6827. Min Act: -0.0000

Data Index: 137911 (The Pile)

Max Activating Token Index: 606

Text #4

Max Range: 0.6827. Min Range: -0.6827

Max Act: 0.5961. Min Act: -0.0000

Data Index: 913560 (The Pile)

Max Activating Token Index: 239

Text #5

Max Range: 0.6827. Min Range: -0.6827

Max Act: 0.6060. Min Act: -0.0000

Data Index: 710596 (The Pile)

Max Activating Token Index: 837

Text #6

Max Range: 0.6827. Min Range: -0.6827

Max Act: 0.6310. Min Act: -0.0000

Data Index: 1320475 (The Pile)

Max Activating Token Index: 952

Text #7

Max Range: 0.6827. Min Range: -0.6827

Max Act: 0.6051. Min Act: -0.0000

Data Index: 984623 (The Pile)

Max Activating Token Index: 183

Text #8

Max Range: 0.6827. Min Range: -0.6827

Max Act: 0.5825. Min Act: -0.0000

Data Index: 472281 (The Pile)

Max Activating Token Index: 709

Text #9

Max Range: 0.6827. Min Range: -0.6827

Max Act: 0.5787. Min Act: -0.0000

Data Index: 1887030 (The Pile)

Max Activating Token Index: 355

Text #10

Max Range: 0.6827. Min Range: -0.6827

Max Act: 0.5921. Min Act: -0.0000

Data Index: 1656349 (The Pile)

Max Activating Token Index: 403

Text #11

Max Range: 0.6827. Min Range: -0.6827

Max Act: 0.5911. Min Act: -0.0000

Data Index: 937864 (The Pile)

Max Activating Token Index: 540

Text #12

Max Range: 0.6827. Min Range: -0.6827

Max Act: 0.5719. Min Act: -0.0000

Data Index: 1198875 (The Pile)

Max Activating Token Index: 450

Text #13

Max Range: 0.6827. Min Range: -0.6827

Max Act: 0.5373. Min Act: -0.0000

Data Index: 1857881 (The Pile)

Max Activating Token Index: 938

Text #14

Max Range: 0.6827. Min Range: -0.6827

Max Act: 0.5468. Min Act: -0.0000

Data Index: 1026405 (The Pile)

Max Activating Token Index: 127

Text #15

Max Range: 0.6827. Min Range: -0.6827

Max Act: 0.5515. Min Act: -0.0000

Data Index: 1021798 (The Pile)

Max Activating Token Index: 435

Text #16

Max Range: 0.6827. Min Range: -0.6827

Max Act: 0.5668. Min Act: -0.0000

Data Index: 1026497 (The Pile)

Max Activating Token Index: 554

Text #17

Max Range: 0.6827. Min Range: -0.6827

Max Act: 0.5473. Min Act: -0.0000

Data Index: 1137411 (The Pile)

Max Activating Token Index: 754

Text #18

Max Range: 0.6827. Min Range: -0.6827

Max Act: 0.5923. Min Act: -0.0000

Data Index: 1440272 (The Pile)

Max Activating Token Index: 243

Text #19

Max Range: 0.6827. Min Range: -0.6827

Max Act: 0.5428. Min Act: -0.0000

Data Index: 765464 (The Pile)

Max Activating Token Index: 120