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

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

Neuron 1857 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2982. Min Range: -1.2982

Max Act: 1.2507. Min Act: -0.0001

Data Index: 1350778 (C4 (Web Text))

Max Activating Token Index: 776

Text #1

Max Range: 1.2982. Min Range: -1.2982

Max Act: 1.2306. Min Act: -0.0001

Data Index: 324815 (C4 (Web Text))

Max Activating Token Index: 342

Text #2

Max Range: 1.2982. Min Range: -1.2982

Max Act: 1.2090. Min Act: -0.0001

Data Index: 144356 (C4 (Web Text))

Max Activating Token Index: 725

Text #3

Max Range: 1.2982. Min Range: -1.2982

Max Act: 1.2982. Min Act: -0.0001

Data Index: 268093 (C4 (Web Text))

Max Activating Token Index: 910

Text #4

Max Range: 1.2982. Min Range: -1.2982

Max Act: 1.2766. Min Act: -0.0001

Data Index: 421671 (C4 (Web Text))

Max Activating Token Index: 737

Text #5

Max Range: 1.2982. Min Range: -1.2982

Max Act: 1.2745. Min Act: -0.0001

Data Index: 725332 (C4 (Web Text))

Max Activating Token Index: 297

Text #6

Max Range: 1.2982. Min Range: -1.2982

Max Act: 1.1955. Min Act: -0.0001

Data Index: 1358323 (C4 (Web Text))

Max Activating Token Index: 127

Text #7

Max Range: 1.2982. Min Range: -1.2982

Max Act: 1.2352. Min Act: -0.0001

Data Index: 1948 (C4 (Web Text))

Max Activating Token Index: 820

Text #8

Max Range: 1.2982. Min Range: -1.2982

Max Act: 1.2641. Min Act: -0.0001

Data Index: 746446 (C4 (Web Text))

Max Activating Token Index: 265

Text #9

Max Range: 1.2982. Min Range: -1.2982

Max Act: 1.1697. Min Act: -0.0001

Data Index: 1134945 (C4 (Web Text))

Max Activating Token Index: 311

Text #10

Max Range: 1.2982. Min Range: -1.2982

Max Act: 1.1177. Min Act: -0.0001

Data Index: 765057 (C4 (Web Text))

Max Activating Token Index: 249

Text #11

Max Range: 1.2982. Min Range: -1.2982

Max Act: 1.2205. Min Act: -0.0001

Data Index: 783388 (C4 (Web Text))

Max Activating Token Index: 813

Text #12

Max Range: 1.2982. Min Range: -1.2982

Max Act: 1.1318. Min Act: -0.0001

Data Index: 335700 (C4 (Web Text))

Max Activating Token Index: 246

Text #13

Max Range: 1.2982. Min Range: -1.2982

Max Act: 1.1412. Min Act: -0.0001

Data Index: 409823 (C4 (Web Text))

Max Activating Token Index: 880

Text #14

Max Range: 1.2982. Min Range: -1.2982

Max Act: 1.1484. Min Act: -0.0001

Data Index: 312725 (C4 (Web Text))

Max Activating Token Index: 960

Text #15

Max Range: 1.2982. Min Range: -1.2982

Max Act: 1.1949. Min Act: -0.0001

Data Index: 839426 (C4 (Web Text))

Max Activating Token Index: 930

Text #16

Max Range: 1.2982. Min Range: -1.2982

Max Act: 1.0586. Min Act: -0.0001

Data Index: 914118 (C4 (Web Text))

Max Activating Token Index: 507

Text #17

Max Range: 1.2982. Min Range: -1.2982

Max Act: 1.1782. Min Act: -0.0001

Data Index: 297565 (C4 (Web Text))

Max Activating Token Index: 140

Text #18

Max Range: 1.2982. Min Range: -1.2982

Max Act: 1.0447. Min Act: -0.0001

Data Index: 110256 (C4 (Web Text))

Max Activating Token Index: 850

Text #19

Max Range: 1.2982. Min Range: -1.2982

Max Act: 1.1759. Min Act: -0.0001

Data Index: 928161 (C4 (Web Text))

Max Activating Token Index: 853