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

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

Neuron 3813 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0501. Min Act: -0.0002

Data Index: 1200686 (C4 (Web Text))

Max Activating Token Index: 44

Text #1

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0422. Min Act: -0.0002

Data Index: 644197 (C4 (Web Text))

Max Activating Token Index: 8

Text #2

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0355. Min Act: -0.0002

Data Index: 866365 (C4 (Web Text))

Max Activating Token Index: 39

Text #3

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0353. Min Act: -0.0002

Data Index: 649266 (C4 (Web Text))

Max Activating Token Index: 599

Text #4

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0344. Min Act: -0.0002

Data Index: 546059 (C4 (Web Text))

Max Activating Token Index: 30

Text #5

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0330. Min Act: -0.0002

Data Index: 635921 (C4 (Web Text))

Max Activating Token Index: 24

Text #6

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0339. Min Act: -0.0002

Data Index: 1054718 (C4 (Web Text))

Max Activating Token Index: 95

Text #7

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0321. Min Act: -0.0002

Data Index: 1300896 (C4 (Web Text))

Max Activating Token Index: 905

Text #8

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0325. Min Act: -0.0002

Data Index: 174549 (C4 (Web Text))

Max Activating Token Index: 38

Text #9

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0313. Min Act: -0.0002

Data Index: 660884 (C4 (Web Text))

Max Activating Token Index: 793

Text #10

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0311. Min Act: -0.0002

Data Index: 907270 (C4 (Web Text))

Max Activating Token Index: 688

Text #11

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0310. Min Act: -0.0002

Data Index: 187283 (C4 (Web Text))

Max Activating Token Index: 839

Text #12

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0310. Min Act: -0.0002

Data Index: 315996 (C4 (Web Text))

Max Activating Token Index: 834

Text #13

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0309. Min Act: -0.0002

Data Index: 1155984 (C4 (Web Text))

Max Activating Token Index: 21

Text #14

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0309. Min Act: -0.0002

Data Index: 682811 (C4 (Web Text))

Max Activating Token Index: 470

Text #15

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0307. Min Act: -0.0002

Data Index: 361882 (C4 (Web Text))

Max Activating Token Index: 81

Text #16

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0306. Min Act: -0.0002

Data Index: 722997 (C4 (Web Text))

Max Activating Token Index: 41

Text #17

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0306. Min Act: -0.0002

Data Index: 647176 (C4 (Web Text))

Max Activating Token Index: 650

Text #18

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0311. Min Act: -0.0002

Data Index: 730244 (C4 (Web Text))

Max Activating Token Index: 65

Text #19

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0305. Min Act: -0.0002

Data Index: 14846 (C4 (Web Text))

Max Activating Token Index: 55