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

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

Neuron 894 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6704. Min Range: -1.6704

Max Act: 1.6704. Min Act: -0.0000

Data Index: 1026557 (C4 (Web Text))

Max Activating Token Index: 443

Text #1

Max Range: 1.6704. Min Range: -1.6704

Max Act: 1.4351. Min Act: -0.0000

Data Index: 520477 (C4 (Web Text))

Max Activating Token Index: 164

Text #2

Max Range: 1.6704. Min Range: -1.6704

Max Act: 1.4016. Min Act: -0.0000

Data Index: 1074057 (C4 (Web Text))

Max Activating Token Index: 255

Text #3

Max Range: 1.6704. Min Range: -1.6704

Max Act: 1.0855. Min Act: 0.0000

Data Index: 1185703 (C4 (Web Text))

Max Activating Token Index: 715

Text #4

Max Range: 1.6704. Min Range: -1.6704

Max Act: 0.9582. Min Act: 0.0000

Data Index: 294755 (C4 (Web Text))

Max Activating Token Index: 185

Text #5

Max Range: 1.6704. Min Range: -1.6704

Max Act: 0.8713. Min Act: 0.0000

Data Index: 178694 (C4 (Web Text))

Max Activating Token Index: 375

Text #6

Max Range: 1.6704. Min Range: -1.6704

Max Act: 0.8358. Min Act: -0.0000

Data Index: 637384 (C4 (Web Text))

Max Activating Token Index: 458

Text #7

Max Range: 1.6704. Min Range: -1.6704

Max Act: 0.8856. Min Act: 0.0000

Data Index: 426831 (C4 (Web Text))

Max Activating Token Index: 765

Text #8

Max Range: 1.6704. Min Range: -1.6704

Max Act: 0.8619. Min Act: 0.0001

Data Index: 913245 (C4 (Web Text))

Max Activating Token Index: 298

Text #9

Max Range: 1.6704. Min Range: -1.6704

Max Act: 0.7958. Min Act: -0.0000

Data Index: 170322 (C4 (Web Text))

Max Activating Token Index: 825

Text #10

Max Range: 1.6704. Min Range: -1.6704

Max Act: 0.8651. Min Act: -0.0000

Data Index: 1127792 (C4 (Web Text))

Max Activating Token Index: 724

Text #11

Max Range: 1.6704. Min Range: -1.6704

Max Act: 0.8820. Min Act: -0.0000

Data Index: 1123090 (C4 (Web Text))

Max Activating Token Index: 35

Text #12

Max Range: 1.6704. Min Range: -1.6704

Max Act: 0.7955. Min Act: -0.0000

Data Index: 1201226 (C4 (Web Text))

Max Activating Token Index: 637

Text #13

Max Range: 1.6704. Min Range: -1.6704

Max Act: 0.6915. Min Act: -0.0000

Data Index: 1187299 (C4 (Web Text))

Max Activating Token Index: 951

Text #14

Max Range: 1.6704. Min Range: -1.6704

Max Act: 0.7236. Min Act: -0.0000

Data Index: 904366 (C4 (Web Text))

Max Activating Token Index: 641

Text #15

Max Range: 1.6704. Min Range: -1.6704

Max Act: 0.7467. Min Act: -0.0000

Data Index: 1163576 (C4 (Web Text))

Max Activating Token Index: 60

Text #16

Max Range: 1.6704. Min Range: -1.6704

Max Act: 0.7441. Min Act: -0.0000

Data Index: 1357665 (C4 (Web Text))

Max Activating Token Index: 652

Text #17

Max Range: 1.6704. Min Range: -1.6704

Max Act: 0.6276. Min Act: 0.0000

Data Index: 1290358 (C4 (Web Text))

Max Activating Token Index: 562

Text #18

Max Range: 1.6704. Min Range: -1.6704

Max Act: 0.6223. Min Act: 0.0000

Data Index: 36905 (C4 (Web Text))

Max Activating Token Index: 33

Text #19

Max Range: 1.6704. Min Range: -1.6704

Max Act: 0.6727. Min Act: -0.0000

Data Index: 68823 (C4 (Web Text))

Max Activating Token Index: 493