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

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

Neuron 4000 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5084. Min Range: -0.5084

Max Act: 0.5084. Min Act: -0.0000

Data Index: 346515 (C4 (Web Text))

Max Activating Token Index: 36

Text #1

Max Range: 0.5084. Min Range: -0.5084

Max Act: 0.4611. Min Act: -0.0000

Data Index: 625333 (C4 (Web Text))

Max Activating Token Index: 869

Text #2

Max Range: 0.5084. Min Range: -0.5084

Max Act: 0.4300. Min Act: -0.0000

Data Index: 704555 (C4 (Web Text))

Max Activating Token Index: 999

Text #3

Max Range: 0.5084. Min Range: -0.5084

Max Act: 0.4249. Min Act: -0.0001

Data Index: 794004 (C4 (Web Text))

Max Activating Token Index: 795

Text #4

Max Range: 0.5084. Min Range: -0.5084

Max Act: 0.4359. Min Act: -0.0001

Data Index: 1215703 (C4 (Web Text))

Max Activating Token Index: 716

Text #5

Max Range: 0.5084. Min Range: -0.5084

Max Act: 0.3679. Min Act: -0.0000

Data Index: 619938 (C4 (Web Text))

Max Activating Token Index: 676

Text #6

Max Range: 0.5084. Min Range: -0.5084

Max Act: 0.3892. Min Act: -0.0000

Data Index: 917123 (C4 (Web Text))

Max Activating Token Index: 807

Text #7

Max Range: 0.5084. Min Range: -0.5084

Max Act: 0.3415. Min Act: -0.0000

Data Index: 101969 (C4 (Web Text))

Max Activating Token Index: 372

Text #8

Max Range: 0.5084. Min Range: -0.5084

Max Act: 0.3596. Min Act: -0.0001

Data Index: 666713 (C4 (Web Text))

Max Activating Token Index: 218

Text #9

Max Range: 0.5084. Min Range: -0.5084

Max Act: 0.3272. Min Act: -0.0000

Data Index: 1082992 (C4 (Web Text))

Max Activating Token Index: 483

Text #10

Max Range: 0.5084. Min Range: -0.5084

Max Act: 0.3194. Min Act: -0.0000

Data Index: 1423 (C4 (Web Text))

Max Activating Token Index: 375

Text #11

Max Range: 0.5084. Min Range: -0.5084

Max Act: 0.3154. Min Act: -0.0001

Data Index: 831897 (C4 (Web Text))

Max Activating Token Index: 817

Text #12

Max Range: 0.5084. Min Range: -0.5084

Max Act: 0.2895. Min Act: -0.0001

Data Index: 1173677 (C4 (Web Text))

Max Activating Token Index: 222

Text #13

Max Range: 0.5084. Min Range: -0.5084

Max Act: 0.2874. Min Act: -0.0000

Data Index: 144564 (C4 (Web Text))

Max Activating Token Index: 37

Text #14

Max Range: 0.5084. Min Range: -0.5084

Max Act: 0.2383. Min Act: -0.0000

Data Index: 210353 (C4 (Web Text))

Max Activating Token Index: 872

Text #15

Max Range: 0.5084. Min Range: -0.5084

Max Act: 0.2397. Min Act: -0.0000

Data Index: 1115133 (C4 (Web Text))

Max Activating Token Index: 919

Text #16

Max Range: 0.5084. Min Range: -0.5084

Max Act: 0.2748. Min Act: -0.0000

Data Index: 925976 (C4 (Web Text))

Max Activating Token Index: 232

Text #17

Max Range: 0.5084. Min Range: -0.5084

Max Act: 0.2924. Min Act: -0.0001

Data Index: 870498 (C4 (Web Text))

Max Activating Token Index: 1018

Text #18

Max Range: 0.5084. Min Range: -0.5084

Max Act: 0.2606. Min Act: -0.0000

Data Index: 853454 (C4 (Web Text))

Max Activating Token Index: 700

Text #19

Max Range: 0.5084. Min Range: -0.5084

Max Act: 0.2496. Min Act: -0.0000

Data Index: 12963 (C4 (Web Text))

Max Activating Token Index: 939