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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1281 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8035. Min Range: -0.8035

Max Act: 0.8035. Min Act: -0.0000

Data Index: 1160585 (C4 (Web Text))

Max Activating Token Index: 56

Text #1

Max Range: 0.8035. Min Range: -0.8035

Max Act: 0.6720. Min Act: -0.0000

Data Index: 284344 (C4 (Web Text))

Max Activating Token Index: 362

Text #2

Max Range: 0.8035. Min Range: -0.8035

Max Act: 0.5904. Min Act: -0.0000

Data Index: 84390 (C4 (Web Text))

Max Activating Token Index: 600

Text #3

Max Range: 0.8035. Min Range: -0.8035

Max Act: 0.6207. Min Act: -0.0000

Data Index: 838447 (C4 (Web Text))

Max Activating Token Index: 545

Text #4

Max Range: 0.8035. Min Range: -0.8035

Max Act: 0.6659. Min Act: -0.0000

Data Index: 324139 (C4 (Web Text))

Max Activating Token Index: 279

Text #5

Max Range: 0.8035. Min Range: -0.8035

Max Act: 0.6081. Min Act: -0.0000

Data Index: 498634 (C4 (Web Text))

Max Activating Token Index: 984

Text #6

Max Range: 0.8035. Min Range: -0.8035

Max Act: 0.5952. Min Act: -0.0000

Data Index: 1109273 (C4 (Web Text))

Max Activating Token Index: 802

Text #7

Max Range: 0.8035. Min Range: -0.8035

Max Act: 0.5942. Min Act: -0.0000

Data Index: 490234 (C4 (Web Text))

Max Activating Token Index: 639

Text #8

Max Range: 0.8035. Min Range: -0.8035

Max Act: 0.5612. Min Act: -0.0000

Data Index: 874878 (C4 (Web Text))

Max Activating Token Index: 796

Text #9

Max Range: 0.8035. Min Range: -0.8035

Max Act: 0.5813. Min Act: -0.0000

Data Index: 49273 (C4 (Web Text))

Max Activating Token Index: 97

Text #10

Max Range: 0.8035. Min Range: -0.8035

Max Act: 0.5791. Min Act: -0.0000

Data Index: 198352 (C4 (Web Text))

Max Activating Token Index: 494

Text #11

Max Range: 0.8035. Min Range: -0.8035

Max Act: 0.5710. Min Act: -0.0000

Data Index: 659698 (C4 (Web Text))

Max Activating Token Index: 1015

Text #12

Max Range: 0.8035. Min Range: -0.8035

Max Act: 0.5482. Min Act: -0.0000

Data Index: 467118 (C4 (Web Text))

Max Activating Token Index: 662

Text #13

Max Range: 0.8035. Min Range: -0.8035

Max Act: 0.5354. Min Act: -0.0000

Data Index: 1153094 (C4 (Web Text))

Max Activating Token Index: 236

Text #14

Max Range: 0.8035. Min Range: -0.8035

Max Act: 0.5466. Min Act: -0.0000

Data Index: 698454 (C4 (Web Text))

Max Activating Token Index: 143

Text #15

Max Range: 0.8035. Min Range: -0.8035

Max Act: 0.5480. Min Act: -0.0000

Data Index: 1156563 (C4 (Web Text))

Max Activating Token Index: 329

Text #16

Max Range: 0.8035. Min Range: -0.8035

Max Act: 0.5186. Min Act: -0.0000

Data Index: 698326 (C4 (Web Text))

Max Activating Token Index: 636

Text #17

Max Range: 0.8035. Min Range: -0.8035

Max Act: 0.4991. Min Act: -0.0000

Data Index: 453920 (C4 (Web Text))

Max Activating Token Index: 388

Text #18

Max Range: 0.8035. Min Range: -0.8035

Max Act: 0.5294. Min Act: -0.0000

Data Index: 490171 (C4 (Web Text))

Max Activating Token Index: 989

Text #19

Max Range: 0.8035. Min Range: -0.8035

Max Act: 0.5109. Min Act: -0.0000

Data Index: 396000 (C4 (Web Text))

Max Activating Token Index: 119