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

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

Neuron 4597 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5447. Min Range: -0.5447

Max Act: 0.5447. Min Act: -0.0000

Data Index: 233926 (C4 (Web Text))

Max Activating Token Index: 9

Text #1

Max Range: 0.5447. Min Range: -0.5447

Max Act: 0.4169. Min Act: -0.0000

Data Index: 714569 (C4 (Web Text))

Max Activating Token Index: 717

Text #2

Max Range: 0.5447. Min Range: -0.5447

Max Act: 0.3768. Min Act: -0.0000

Data Index: 696927 (C4 (Web Text))

Max Activating Token Index: 581

Text #3

Max Range: 0.5447. Min Range: -0.5447

Max Act: 0.3852. Min Act: -0.0000

Data Index: 643072 (C4 (Web Text))

Max Activating Token Index: 679

Text #4

Max Range: 0.5447. Min Range: -0.5447

Max Act: 0.3819. Min Act: -0.0000

Data Index: 1251260 (C4 (Web Text))

Max Activating Token Index: 49

Text #5

Max Range: 0.5447. Min Range: -0.5447

Max Act: 0.4040. Min Act: -0.0000

Data Index: 226426 (C4 (Web Text))

Max Activating Token Index: 941

Text #6

Max Range: 0.5447. Min Range: -0.5447

Max Act: 0.3627. Min Act: -0.0000

Data Index: 265910 (C4 (Web Text))

Max Activating Token Index: 100

Text #7

Max Range: 0.5447. Min Range: -0.5447

Max Act: 0.3441. Min Act: -0.0000

Data Index: 1109526 (C4 (Web Text))

Max Activating Token Index: 602

Text #8

Max Range: 0.5447. Min Range: -0.5447

Max Act: 0.3992. Min Act: -0.0000

Data Index: 682099 (C4 (Web Text))

Max Activating Token Index: 426

Text #9

Max Range: 0.5447. Min Range: -0.5447

Max Act: 0.3546. Min Act: -0.0000

Data Index: 862631 (C4 (Web Text))

Max Activating Token Index: 1017

Text #10

Max Range: 0.5447. Min Range: -0.5447

Max Act: 0.3511. Min Act: -0.0000

Data Index: 1149221 (C4 (Web Text))

Max Activating Token Index: 1005

Text #11

Max Range: 0.5447. Min Range: -0.5447

Max Act: 0.3477. Min Act: -0.0000

Data Index: 1193727 (C4 (Web Text))

Max Activating Token Index: 576

Text #12

Max Range: 0.5447. Min Range: -0.5447

Max Act: 0.3487. Min Act: -0.0000

Data Index: 294195 (C4 (Web Text))

Max Activating Token Index: 794

Text #13

Max Range: 0.5447. Min Range: -0.5447

Max Act: 0.3351. Min Act: -0.0000

Data Index: 389358 (C4 (Web Text))

Max Activating Token Index: 1004

Text #14

Max Range: 0.5447. Min Range: -0.5447

Max Act: 0.3230. Min Act: -0.0000

Data Index: 1070732 (C4 (Web Text))

Max Activating Token Index: 573

Text #15

Max Range: 0.5447. Min Range: -0.5447

Max Act: 0.3441. Min Act: -0.0000

Data Index: 1086021 (C4 (Web Text))

Max Activating Token Index: 972

Text #16

Max Range: 0.5447. Min Range: -0.5447

Max Act: 0.3249. Min Act: -0.0000

Data Index: 95684 (C4 (Web Text))

Max Activating Token Index: 788

Text #17

Max Range: 0.5447. Min Range: -0.5447

Max Act: 0.3292. Min Act: -0.0000

Data Index: 535501 (C4 (Web Text))

Max Activating Token Index: 207

Text #18

Max Range: 0.5447. Min Range: -0.5447

Max Act: 0.3146. Min Act: -0.0000

Data Index: 50859 (C4 (Web Text))

Max Activating Token Index: 88

Text #19

Max Range: 0.5447. Min Range: -0.5447

Max Act: 0.3371. Min Act: -0.0000

Data Index: 45097 (C4 (Web Text))

Max Activating Token Index: 508