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

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

Neuron 877 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9621. Min Range: -0.9621

Max Act: 0.9283. Min Act: -0.0000

Data Index: 733091 (C4 (Web Text))

Max Activating Token Index: 819

Text #1

Max Range: 0.9621. Min Range: -0.9621

Max Act: 0.9621. Min Act: -0.0000

Data Index: 203566 (C4 (Web Text))

Max Activating Token Index: 401

Text #2

Max Range: 0.9621. Min Range: -0.9621

Max Act: 0.8129. Min Act: -0.0000

Data Index: 1079672 (C4 (Web Text))

Max Activating Token Index: 394

Text #3

Max Range: 0.9621. Min Range: -0.9621

Max Act: 0.7721. Min Act: -0.0000

Data Index: 896523 (C4 (Web Text))

Max Activating Token Index: 974

Text #4

Max Range: 0.9621. Min Range: -0.9621

Max Act: 0.7806. Min Act: -0.0000

Data Index: 71277 (C4 (Web Text))

Max Activating Token Index: 518

Text #5

Max Range: 0.9621. Min Range: -0.9621

Max Act: 0.7720. Min Act: -0.0000

Data Index: 101908 (C4 (Web Text))

Max Activating Token Index: 286

Text #6

Max Range: 0.9621. Min Range: -0.9621

Max Act: 0.7463. Min Act: -0.0000

Data Index: 755418 (C4 (Web Text))

Max Activating Token Index: 828

Text #7

Max Range: 0.9621. Min Range: -0.9621

Max Act: 0.7859. Min Act: -0.0000

Data Index: 1189145 (C4 (Web Text))

Max Activating Token Index: 903

Text #8

Max Range: 0.9621. Min Range: -0.9621

Max Act: 0.7527. Min Act: -0.0000

Data Index: 605982 (C4 (Web Text))

Max Activating Token Index: 726

Text #9

Max Range: 0.9621. Min Range: -0.9621

Max Act: 0.7423. Min Act: -0.0000

Data Index: 668700 (C4 (Web Text))

Max Activating Token Index: 588

Text #10

Max Range: 0.9621. Min Range: -0.9621

Max Act: 0.7205. Min Act: -0.0000

Data Index: 506271 (C4 (Web Text))

Max Activating Token Index: 962

Text #11

Max Range: 0.9621. Min Range: -0.9621

Max Act: 0.7399. Min Act: -0.0000

Data Index: 890982 (C4 (Web Text))

Max Activating Token Index: 398

Text #12

Max Range: 0.9621. Min Range: -0.9621

Max Act: 0.7397. Min Act: -0.0000

Data Index: 944714 (C4 (Web Text))

Max Activating Token Index: 995

Text #13

Max Range: 0.9621. Min Range: -0.9621

Max Act: 0.7138. Min Act: -0.0000

Data Index: 1247980 (C4 (Web Text))

Max Activating Token Index: 753

Text #14

Max Range: 0.9621. Min Range: -0.9621

Max Act: 0.7021. Min Act: -0.0000

Data Index: 239866 (C4 (Web Text))

Max Activating Token Index: 228

Text #15

Max Range: 0.9621. Min Range: -0.9621

Max Act: 0.6780. Min Act: 0.0000

Data Index: 32332 (C4 (Web Text))

Max Activating Token Index: 1006

Text #16

Max Range: 0.9621. Min Range: -0.9621

Max Act: 0.6707. Min Act: 0.0000

Data Index: 1100457 (C4 (Web Text))

Max Activating Token Index: 401

Text #17

Max Range: 0.9621. Min Range: -0.9621

Max Act: 0.6669. Min Act: -0.0000

Data Index: 114356 (C4 (Web Text))

Max Activating Token Index: 676

Text #18

Max Range: 0.9621. Min Range: -0.9621

Max Act: 0.6713. Min Act: -0.0000

Data Index: 1213885 (C4 (Web Text))

Max Activating Token Index: 895

Text #19

Max Range: 0.9621. Min Range: -0.9621

Max Act: 0.6613. Min Act: -0.0000

Data Index: 752003 (C4 (Web Text))

Max Activating Token Index: 680