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

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

Neuron 4657 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0954. Min Range: -0.0954

Max Act: 0.0929. Min Act: -0.0002

Data Index: 278917 (C4 (Web Text))

Max Activating Token Index: 837

Text #1

Max Range: 0.0954. Min Range: -0.0954

Max Act: 0.0886. Min Act: -0.0002

Data Index: 461723 (C4 (Web Text))

Max Activating Token Index: 545

Text #2

Max Range: 0.0954. Min Range: -0.0954

Max Act: 0.0843. Min Act: -0.0002

Data Index: 643890 (C4 (Web Text))

Max Activating Token Index: 496

Text #3

Max Range: 0.0954. Min Range: -0.0954

Max Act: 0.0928. Min Act: -0.0002

Data Index: 356531 (C4 (Web Text))

Max Activating Token Index: 551

Text #4

Max Range: 0.0954. Min Range: -0.0954

Max Act: 0.0935. Min Act: -0.0002

Data Index: 209587 (C4 (Web Text))

Max Activating Token Index: 414

Text #5

Max Range: 0.0954. Min Range: -0.0954

Max Act: 0.0944. Min Act: -0.0002

Data Index: 1146521 (C4 (Web Text))

Max Activating Token Index: 439

Text #6

Max Range: 0.0954. Min Range: -0.0954

Max Act: 0.0921. Min Act: -0.0002

Data Index: 25541 (C4 (Web Text))

Max Activating Token Index: 177

Text #7

Max Range: 0.0954. Min Range: -0.0954

Max Act: 0.0954. Min Act: -0.0002

Data Index: 980759 (C4 (Web Text))

Max Activating Token Index: 288

Text #8

Max Range: 0.0954. Min Range: -0.0954

Max Act: 0.0848. Min Act: -0.0002

Data Index: 281073 (C4 (Web Text))

Max Activating Token Index: 926

Text #9

Max Range: 0.0954. Min Range: -0.0954

Max Act: 0.0877. Min Act: -0.0002

Data Index: 516233 (C4 (Web Text))

Max Activating Token Index: 248

Text #10

Max Range: 0.0954. Min Range: -0.0954

Max Act: 0.0847. Min Act: -0.0002

Data Index: 833599 (C4 (Web Text))

Max Activating Token Index: 281

Text #11

Max Range: 0.0954. Min Range: -0.0954

Max Act: 0.0809. Min Act: -0.0002

Data Index: 1166801 (C4 (Web Text))

Max Activating Token Index: 912

Text #12

Max Range: 0.0954. Min Range: -0.0954

Max Act: 0.0624. Min Act: -0.0002

Data Index: 588309 (C4 (Web Text))

Max Activating Token Index: 143

Text #13

Max Range: 0.0954. Min Range: -0.0954

Max Act: 0.0893. Min Act: -0.0002

Data Index: 667168 (C4 (Web Text))

Max Activating Token Index: 628

Text #14

Max Range: 0.0954. Min Range: -0.0954

Max Act: 0.0952. Min Act: -0.0002

Data Index: 250184 (C4 (Web Text))

Max Activating Token Index: 246

Text #15

Max Range: 0.0954. Min Range: -0.0954

Max Act: 0.0425. Min Act: -0.0002

Data Index: 767467 (C4 (Web Text))

Max Activating Token Index: 279

Text #16

Max Range: 0.0954. Min Range: -0.0954

Max Act: 0.0730. Min Act: -0.0002

Data Index: 1345780 (C4 (Web Text))

Max Activating Token Index: 678

Text #17

Max Range: 0.0954. Min Range: -0.0954

Max Act: 0.0862. Min Act: -0.0002

Data Index: 1201185 (C4 (Web Text))

Max Activating Token Index: 999

Text #18

Max Range: 0.0954. Min Range: -0.0954

Max Act: 0.0691. Min Act: -0.0002

Data Index: 105470 (C4 (Web Text))

Max Activating Token Index: 307

Text #19

Max Range: 0.0954. Min Range: -0.0954

Max Act: 0.0711. Min Act: -0.0002

Data Index: 1335411 (C4 (Web Text))

Max Activating Token Index: 229