Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 6025 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.5427. Min Range: -2.5427

Max Act: 2.5427. Min Act: -0.0000

Data Index: 672484 (C4 (Web Text))

Max Activating Token Index: 946

Text #1

Max Range: 2.5427. Min Range: -2.5427

Max Act: 2.3483. Min Act: -0.0000

Data Index: 1243356 (C4 (Web Text))

Max Activating Token Index: 650

Text #2

Max Range: 2.5427. Min Range: -2.5427

Max Act: 2.5408. Min Act: -0.0000

Data Index: 1071843 (C4 (Web Text))

Max Activating Token Index: 810

Text #3

Max Range: 2.5427. Min Range: -2.5427

Max Act: 2.2716. Min Act: -0.0000

Data Index: 1353640 (C4 (Web Text))

Max Activating Token Index: 873

Text #4

Max Range: 2.5427. Min Range: -2.5427

Max Act: 2.0371. Min Act: -0.0000

Data Index: 542197 (C4 (Web Text))

Max Activating Token Index: 651

Text #5

Max Range: 2.5427. Min Range: -2.5427

Max Act: 1.9855. Min Act: -0.0000

Data Index: 1053257 (C4 (Web Text))

Max Activating Token Index: 179

Text #6

Max Range: 2.5427. Min Range: -2.5427

Max Act: 2.0880. Min Act: -0.0000

Data Index: 1332945 (C4 (Web Text))

Max Activating Token Index: 737

Text #7

Max Range: 2.5427. Min Range: -2.5427

Max Act: 2.0296. Min Act: -0.0000

Data Index: 217173 (C4 (Web Text))

Max Activating Token Index: 156

Text #8

Max Range: 2.5427. Min Range: -2.5427

Max Act: 2.0026. Min Act: -0.0000

Data Index: 196635 (C4 (Web Text))

Max Activating Token Index: 430

Text #9

Max Range: 2.5427. Min Range: -2.5427

Max Act: 1.8794. Min Act: -0.0000

Data Index: 724680 (C4 (Web Text))

Max Activating Token Index: 542

Text #10

Max Range: 2.5427. Min Range: -2.5427

Max Act: 1.9363. Min Act: -0.0000

Data Index: 865626 (C4 (Web Text))

Max Activating Token Index: 676

Text #11

Max Range: 2.5427. Min Range: -2.5427

Max Act: 1.8103. Min Act: -0.0000

Data Index: 611633 (C4 (Web Text))

Max Activating Token Index: 459

Text #12

Max Range: 2.5427. Min Range: -2.5427

Max Act: 2.0023. Min Act: -0.0000

Data Index: 281049 (C4 (Web Text))

Max Activating Token Index: 782

Text #13

Max Range: 2.5427. Min Range: -2.5427

Max Act: 1.9674. Min Act: -0.0000

Data Index: 112807 (C4 (Web Text))

Max Activating Token Index: 853

Text #14

Max Range: 2.5427. Min Range: -2.5427

Max Act: 1.7960. Min Act: -0.0000

Data Index: 319604 (C4 (Web Text))

Max Activating Token Index: 201

Text #15

Max Range: 2.5427. Min Range: -2.5427

Max Act: 1.7126. Min Act: -0.0000

Data Index: 1312600 (C4 (Web Text))

Max Activating Token Index: 425

Text #16

Max Range: 2.5427. Min Range: -2.5427

Max Act: 1.7843. Min Act: -0.0000

Data Index: 241843 (C4 (Web Text))

Max Activating Token Index: 461

Text #17

Max Range: 2.5427. Min Range: -2.5427

Max Act: 1.7759. Min Act: -0.0000

Data Index: 726229 (C4 (Web Text))

Max Activating Token Index: 612

Text #18

Max Range: 2.5427. Min Range: -2.5427

Max Act: 1.8127. Min Act: -0.0000

Data Index: 206509 (C4 (Web Text))

Max Activating Token Index: 82

Text #19

Max Range: 2.5427. Min Range: -2.5427

Max Act: 1.7962. Min Act: -0.0000

Data Index: 389983 (C4 (Web Text))

Max Activating Token Index: 338