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

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

Neuron 1847 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0355. Min Act: -0.0002

Data Index: 1259504 (C4 (Web Text))

Max Activating Token Index: 485

Text #1

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0353. Min Act: -0.0002

Data Index: 194867 (C4 (Web Text))

Max Activating Token Index: 610

Text #2

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0314. Min Act: -0.0002

Data Index: 720444 (C4 (Web Text))

Max Activating Token Index: 584

Text #3

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0294. Min Act: -0.0002

Data Index: 469381 (C4 (Web Text))

Max Activating Token Index: 36

Text #4

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0297. Min Act: -0.0002

Data Index: 1284548 (C4 (Web Text))

Max Activating Token Index: 121

Text #5

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0276. Min Act: -0.0002

Data Index: 1268762 (C4 (Web Text))

Max Activating Token Index: 454

Text #6

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0291. Min Act: -0.0002

Data Index: 746267 (C4 (Web Text))

Max Activating Token Index: 386

Text #7

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0301. Min Act: -0.0002

Data Index: 1242920 (C4 (Web Text))

Max Activating Token Index: 853

Text #8

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0287. Min Act: -0.0002

Data Index: 1096104 (C4 (Web Text))

Max Activating Token Index: 698

Text #9

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0271. Min Act: -0.0002

Data Index: 730915 (C4 (Web Text))

Max Activating Token Index: 806

Text #10

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0259. Min Act: -0.0002

Data Index: 465846 (C4 (Web Text))

Max Activating Token Index: 307

Text #11

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0263. Min Act: -0.0002

Data Index: 1035787 (C4 (Web Text))

Max Activating Token Index: 118

Text #12

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0271. Min Act: -0.0002

Data Index: 102724 (C4 (Web Text))

Max Activating Token Index: 500

Text #13

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0280. Min Act: -0.0002

Data Index: 500551 (C4 (Web Text))

Max Activating Token Index: 89

Text #14

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0271. Min Act: -0.0002

Data Index: 1027335 (C4 (Web Text))

Max Activating Token Index: 251

Text #15

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0270. Min Act: -0.0002

Data Index: 735848 (C4 (Web Text))

Max Activating Token Index: 630

Text #16

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0264. Min Act: -0.0002

Data Index: 51224 (C4 (Web Text))

Max Activating Token Index: 559

Text #17

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0270. Min Act: -0.0002

Data Index: 1241820 (C4 (Web Text))

Max Activating Token Index: 398

Text #18

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0262. Min Act: -0.0002

Data Index: 1326841 (C4 (Web Text))

Max Activating Token Index: 626

Text #19

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0256. Min Act: -0.0002

Data Index: 961853 (C4 (Web Text))

Max Activating Token Index: 273