Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1419 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1032. Min Range: -0.1032

Max Act: 0.1032. Min Act: -0.0002

Data Index: 470393 (C4 (Web Text))

Max Activating Token Index: 285

Text #1

Max Range: 0.1032. Min Range: -0.1032

Max Act: 0.0961. Min Act: -0.0002

Data Index: 121745 (C4 (Web Text))

Max Activating Token Index: 290

Text #2

Max Range: 0.1032. Min Range: -0.1032

Max Act: 0.0977. Min Act: -0.0002

Data Index: 338574 (C4 (Web Text))

Max Activating Token Index: 83

Text #3

Max Range: 0.1032. Min Range: -0.1032

Max Act: 0.0944. Min Act: -0.0002

Data Index: 601683 (C4 (Web Text))

Max Activating Token Index: 92

Text #4

Max Range: 0.1032. Min Range: -0.1032

Max Act: 0.0958. Min Act: -0.0002

Data Index: 776786 (C4 (Web Text))

Max Activating Token Index: 234

Text #5

Max Range: 0.1032. Min Range: -0.1032

Max Act: 0.0948. Min Act: -0.0002

Data Index: 1157454 (C4 (Web Text))

Max Activating Token Index: 152

Text #6

Max Range: 0.1032. Min Range: -0.1032

Max Act: 0.0891. Min Act: -0.0002

Data Index: 620422 (C4 (Web Text))

Max Activating Token Index: 872

Text #7

Max Range: 0.1032. Min Range: -0.1032

Max Act: 0.0922. Min Act: -0.0002

Data Index: 1239878 (C4 (Web Text))

Max Activating Token Index: 869

Text #8

Max Range: 0.1032. Min Range: -0.1032

Max Act: 0.0914. Min Act: -0.0002

Data Index: 428658 (C4 (Web Text))

Max Activating Token Index: 204

Text #9

Max Range: 0.1032. Min Range: -0.1032

Max Act: 0.0934. Min Act: -0.0002

Data Index: 806623 (C4 (Web Text))

Max Activating Token Index: 871

Text #10

Max Range: 0.1032. Min Range: -0.1032

Max Act: 0.0888. Min Act: -0.0002

Data Index: 233920 (C4 (Web Text))

Max Activating Token Index: 515

Text #11

Max Range: 0.1032. Min Range: -0.1032

Max Act: 0.0895. Min Act: -0.0002

Data Index: 1216488 (C4 (Web Text))

Max Activating Token Index: 906

Text #12

Max Range: 0.1032. Min Range: -0.1032

Max Act: 0.0861. Min Act: -0.0002

Data Index: 696788 (C4 (Web Text))

Max Activating Token Index: 859

Text #13

Max Range: 0.1032. Min Range: -0.1032

Max Act: 0.0908. Min Act: -0.0002

Data Index: 901150 (C4 (Web Text))

Max Activating Token Index: 233

Text #14

Max Range: 0.1032. Min Range: -0.1032

Max Act: 0.0879. Min Act: -0.0002

Data Index: 129144 (C4 (Web Text))

Max Activating Token Index: 335

Text #15

Max Range: 0.1032. Min Range: -0.1032

Max Act: 0.0845. Min Act: -0.0002

Data Index: 1304171 (C4 (Web Text))

Max Activating Token Index: 686

Text #16

Max Range: 0.1032. Min Range: -0.1032

Max Act: 0.0875. Min Act: -0.0002

Data Index: 856960 (C4 (Web Text))

Max Activating Token Index: 511

Text #17

Max Range: 0.1032. Min Range: -0.1032

Max Act: 0.0878. Min Act: -0.0002

Data Index: 948616 (C4 (Web Text))

Max Activating Token Index: 593

Text #18

Max Range: 0.1032. Min Range: -0.1032

Max Act: 0.0841. Min Act: -0.0002

Data Index: 301427 (C4 (Web Text))

Max Activating Token Index: 406

Text #19

Max Range: 0.1032. Min Range: -0.1032

Max Act: 0.0871. Min Act: -0.0002

Data Index: 455328 (C4 (Web Text))

Max Activating Token Index: 806