Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2415 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.1069. Min Act: -0.0002

Data Index: 243830 (C4 (Web Text))

Max Activating Token Index: 541

Text #1

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.1059. Min Act: -0.0003

Data Index: 1175822 (C4 (Web Text))

Max Activating Token Index: 380

Text #2

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.1050. Min Act: -0.0002

Data Index: 1250435 (C4 (Web Text))

Max Activating Token Index: 540

Text #3

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0950. Min Act: -0.0003

Data Index: 1046601 (C4 (Web Text))

Max Activating Token Index: 870

Text #4

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0944. Min Act: -0.0002

Data Index: 1148318 (C4 (Web Text))

Max Activating Token Index: 725

Text #5

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0939. Min Act: -0.0002

Data Index: 835401 (C4 (Web Text))

Max Activating Token Index: 36

Text #6

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0937. Min Act: -0.0003

Data Index: 45385 (C4 (Web Text))

Max Activating Token Index: 31

Text #7

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0934. Min Act: -0.0002

Data Index: 472162 (C4 (Web Text))

Max Activating Token Index: 155

Text #8

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0934. Min Act: -0.0002

Data Index: 570171 (C4 (Web Text))

Max Activating Token Index: 719

Text #9

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0934. Min Act: -0.0002

Data Index: 312896 (C4 (Web Text))

Max Activating Token Index: 121

Text #10

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0886. Min Act: -0.0002

Data Index: 525844 (C4 (Web Text))

Max Activating Token Index: 645

Text #11

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0919. Min Act: -0.0003

Data Index: 1179988 (C4 (Web Text))

Max Activating Token Index: 641

Text #12

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0915. Min Act: -0.0002

Data Index: 793726 (C4 (Web Text))

Max Activating Token Index: 742

Text #13

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0911. Min Act: -0.0003

Data Index: 1329205 (C4 (Web Text))

Max Activating Token Index: 532

Text #14

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0911. Min Act: -0.0003

Data Index: 282666 (C4 (Web Text))

Max Activating Token Index: 694

Text #15

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0894. Min Act: -0.0003

Data Index: 1333115 (C4 (Web Text))

Max Activating Token Index: 703

Text #16

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0888. Min Act: -0.0003

Data Index: 369958 (C4 (Web Text))

Max Activating Token Index: 789

Text #17

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0888. Min Act: -0.0002

Data Index: 597282 (C4 (Web Text))

Max Activating Token Index: 756

Text #18

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0878. Min Act: -0.0002

Data Index: 745425 (C4 (Web Text))

Max Activating Token Index: 666

Text #19

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0878. Min Act: -0.0003

Data Index: 659286 (C4 (Web Text))

Max Activating Token Index: 546