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

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

Neuron 2741 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: 0.9437. Min Range: -0.9437

Max Act: 0.9437. Min Act: -0.0002

Data Index: 847582 (C4 (Web Text))

Max Activating Token Index: 952

Text #1

Max Range: 0.9437. Min Range: -0.9437

Max Act: 0.8383. Min Act: -0.0002

Data Index: 886965 (C4 (Web Text))

Max Activating Token Index: 940

Text #2

Max Range: 0.9437. Min Range: -0.9437

Max Act: 0.7832. Min Act: -0.0002

Data Index: 302328 (C4 (Web Text))

Max Activating Token Index: 553

Text #3

Max Range: 0.9437. Min Range: -0.9437

Max Act: 0.8473. Min Act: -0.0002

Data Index: 1180635 (C4 (Web Text))

Max Activating Token Index: 816

Text #4

Max Range: 0.9437. Min Range: -0.9437

Max Act: 0.7928. Min Act: -0.0002

Data Index: 373663 (C4 (Web Text))

Max Activating Token Index: 777

Text #5

Max Range: 0.9437. Min Range: -0.9437

Max Act: 0.8048. Min Act: -0.0002

Data Index: 388736 (C4 (Web Text))

Max Activating Token Index: 165

Text #6

Max Range: 0.9437. Min Range: -0.9437

Max Act: 0.7512. Min Act: -0.0002

Data Index: 610976 (C4 (Web Text))

Max Activating Token Index: 395

Text #7

Max Range: 0.9437. Min Range: -0.9437

Max Act: 0.7350. Min Act: -0.0002

Data Index: 197740 (C4 (Web Text))

Max Activating Token Index: 876

Text #8

Max Range: 0.9437. Min Range: -0.9437

Max Act: 0.7307. Min Act: -0.0002

Data Index: 1240122 (C4 (Web Text))

Max Activating Token Index: 714

Text #9

Max Range: 0.9437. Min Range: -0.9437

Max Act: 0.8085. Min Act: -0.0002

Data Index: 1173844 (C4 (Web Text))

Max Activating Token Index: 868

Text #10

Max Range: 0.9437. Min Range: -0.9437

Max Act: 0.7479. Min Act: -0.0002

Data Index: 679224 (C4 (Web Text))

Max Activating Token Index: 506

Text #11

Max Range: 0.9437. Min Range: -0.9437

Max Act: 0.7048. Min Act: -0.0002

Data Index: 80530 (C4 (Web Text))

Max Activating Token Index: 254

Text #12

Max Range: 0.9437. Min Range: -0.9437

Max Act: 0.7393. Min Act: -0.0002

Data Index: 859494 (C4 (Web Text))

Max Activating Token Index: 989

Text #13

Max Range: 0.9437. Min Range: -0.9437

Max Act: 0.6981. Min Act: -0.0002

Data Index: 389023 (C4 (Web Text))

Max Activating Token Index: 570

Text #14

Max Range: 0.9437. Min Range: -0.9437

Max Act: 0.7378. Min Act: -0.0003

Data Index: 29143 (C4 (Web Text))

Max Activating Token Index: 690

Text #15

Max Range: 0.9437. Min Range: -0.9437

Max Act: 0.7242. Min Act: -0.0002

Data Index: 811849 (C4 (Web Text))

Max Activating Token Index: 976

Text #16

Max Range: 0.9437. Min Range: -0.9437

Max Act: 0.7227. Min Act: -0.0002

Data Index: 311866 (C4 (Web Text))

Max Activating Token Index: 835

Text #17

Max Range: 0.9437. Min Range: -0.9437

Max Act: 0.7073. Min Act: -0.0002

Data Index: 656381 (C4 (Web Text))

Max Activating Token Index: 722

Text #18

Max Range: 0.9437. Min Range: -0.9437

Max Act: 0.7017. Min Act: -0.0002

Data Index: 184007 (C4 (Web Text))

Max Activating Token Index: 551

Text #19

Max Range: 0.9437. Min Range: -0.9437

Max Act: 0.6874. Min Act: -0.0002

Data Index: 781836 (C4 (Web Text))

Max Activating Token Index: 962