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

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

Neuron 5585 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2985. Min Range: -0.2985

Max Act: 0.2985. Min Act: -0.0000

Data Index: 1211356 (C4 (Web Text))

Max Activating Token Index: 469

Text #1

Max Range: 0.2985. Min Range: -0.2985

Max Act: 0.2923. Min Act: -0.0000

Data Index: 872593 (C4 (Web Text))

Max Activating Token Index: 197

Text #2

Max Range: 0.2985. Min Range: -0.2985

Max Act: 0.2925. Min Act: -0.0000

Data Index: 766606 (C4 (Web Text))

Max Activating Token Index: 878

Text #3

Max Range: 0.2985. Min Range: -0.2985

Max Act: 0.2743. Min Act: -0.0000

Data Index: 623739 (C4 (Web Text))

Max Activating Token Index: 886

Text #4

Max Range: 0.2985. Min Range: -0.2985

Max Act: 0.2580. Min Act: -0.0000

Data Index: 904290 (C4 (Web Text))

Max Activating Token Index: 927

Text #5

Max Range: 0.2985. Min Range: -0.2985

Max Act: 0.2541. Min Act: -0.0000

Data Index: 711175 (C4 (Web Text))

Max Activating Token Index: 150

Text #6

Max Range: 0.2985. Min Range: -0.2985

Max Act: 0.2432. Min Act: -0.0000

Data Index: 411752 (C4 (Web Text))

Max Activating Token Index: 626

Text #7

Max Range: 0.2985. Min Range: -0.2985

Max Act: 0.2402. Min Act: -0.0000

Data Index: 330487 (C4 (Web Text))

Max Activating Token Index: 399

Text #8

Max Range: 0.2985. Min Range: -0.2985

Max Act: 0.2313. Min Act: -0.0000

Data Index: 743869 (C4 (Web Text))

Max Activating Token Index: 355

Text #9

Max Range: 0.2985. Min Range: -0.2985

Max Act: 0.2370. Min Act: -0.0000

Data Index: 747569 (C4 (Web Text))

Max Activating Token Index: 12

Text #10

Max Range: 0.2985. Min Range: -0.2985

Max Act: 0.2360. Min Act: -0.0000

Data Index: 75274 (C4 (Web Text))

Max Activating Token Index: 87

Text #11

Max Range: 0.2985. Min Range: -0.2985

Max Act: 0.2390. Min Act: -0.0000

Data Index: 866039 (C4 (Web Text))

Max Activating Token Index: 121

Text #12

Max Range: 0.2985. Min Range: -0.2985

Max Act: 0.2376. Min Act: -0.0000

Data Index: 126897 (C4 (Web Text))

Max Activating Token Index: 737

Text #13

Max Range: 0.2985. Min Range: -0.2985

Max Act: 0.2284. Min Act: -0.0000

Data Index: 71637 (C4 (Web Text))

Max Activating Token Index: 373

Text #14

Max Range: 0.2985. Min Range: -0.2985

Max Act: 0.2291. Min Act: -0.0000

Data Index: 570467 (C4 (Web Text))

Max Activating Token Index: 485

Text #15

Max Range: 0.2985. Min Range: -0.2985

Max Act: 0.2217. Min Act: -0.0000

Data Index: 1198790 (C4 (Web Text))

Max Activating Token Index: 108

Text #16

Max Range: 0.2985. Min Range: -0.2985

Max Act: 0.2215. Min Act: -0.0000

Data Index: 42886 (C4 (Web Text))

Max Activating Token Index: 209

Text #17

Max Range: 0.2985. Min Range: -0.2985

Max Act: 0.2196. Min Act: -0.0000

Data Index: 188947 (C4 (Web Text))

Max Activating Token Index: 617

Text #18

Max Range: 0.2985. Min Range: -0.2985

Max Act: 0.2172. Min Act: -0.0000

Data Index: 1119089 (C4 (Web Text))

Max Activating Token Index: 488

Text #19

Max Range: 0.2985. Min Range: -0.2985

Max Act: 0.2202. Min Act: -0.0000

Data Index: 1063768 (C4 (Web Text))

Max Activating Token Index: 370