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

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

Neuron 1359 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.1021. Min Act: -0.0005

Data Index: 231962 (C4 (Web Text))

Max Activating Token Index: 291

Text #1

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.1025. Min Act: -0.0005

Data Index: 1023780 (C4 (Web Text))

Max Activating Token Index: 261

Text #2

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0961. Min Act: -0.0005

Data Index: 196068 (C4 (Web Text))

Max Activating Token Index: 599

Text #3

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0843. Min Act: -0.0005

Data Index: 212737 (C4 (Web Text))

Max Activating Token Index: 912

Text #4

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0952. Min Act: -0.0005

Data Index: 520402 (C4 (Web Text))

Max Activating Token Index: 241

Text #5

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0927. Min Act: -0.0005

Data Index: 801463 (C4 (Web Text))

Max Activating Token Index: 85

Text #6

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0926. Min Act: -0.0005

Data Index: 181846 (C4 (Web Text))

Max Activating Token Index: 329

Text #7

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0885. Min Act: -0.0005

Data Index: 141667 (C4 (Web Text))

Max Activating Token Index: 629

Text #8

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0970. Min Act: -0.0005

Data Index: 824253 (C4 (Web Text))

Max Activating Token Index: 1011

Text #9

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0927. Min Act: -0.0005

Data Index: 981590 (C4 (Web Text))

Max Activating Token Index: 455

Text #10

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0866. Min Act: -0.0005

Data Index: 712924 (C4 (Web Text))

Max Activating Token Index: 264

Text #11

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0897. Min Act: -0.0005

Data Index: 1179547 (C4 (Web Text))

Max Activating Token Index: 388

Text #12

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0929. Min Act: -0.0005

Data Index: 874610 (C4 (Web Text))

Max Activating Token Index: 753

Text #13

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0899. Min Act: -0.0004

Data Index: 249027 (C4 (Web Text))

Max Activating Token Index: 704

Text #14

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0817. Min Act: -0.0005

Data Index: 545905 (C4 (Web Text))

Max Activating Token Index: 942

Text #15

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0876. Min Act: -0.0005

Data Index: 728126 (C4 (Web Text))

Max Activating Token Index: 755

Text #16

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0869. Min Act: -0.0005

Data Index: 623367 (C4 (Web Text))

Max Activating Token Index: 916

Text #17

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0906. Min Act: -0.0005

Data Index: 623334 (C4 (Web Text))

Max Activating Token Index: 812

Text #18

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0862. Min Act: -0.0005

Data Index: 147553 (C4 (Web Text))

Max Activating Token Index: 204

Text #19

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0878. Min Act: -0.0005

Data Index: 757546 (C4 (Web Text))

Max Activating Token Index: 245