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

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

Neuron 3794 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: 0.0402. Min Range: -0.0402

Max Act: 0.0402. Min Act: -0.0002

Data Index: 1262831 (C4 (Web Text))

Max Activating Token Index: 253

Text #1

Max Range: 0.0402. Min Range: -0.0402

Max Act: 0.0363. Min Act: -0.0002

Data Index: 1136228 (C4 (Web Text))

Max Activating Token Index: 147

Text #2

Max Range: 0.0402. Min Range: -0.0402

Max Act: 0.0349. Min Act: -0.0002

Data Index: 1283246 (C4 (Web Text))

Max Activating Token Index: 25

Text #3

Max Range: 0.0402. Min Range: -0.0402

Max Act: 0.0326. Min Act: -0.0002

Data Index: 854810 (C4 (Web Text))

Max Activating Token Index: 79

Text #4

Max Range: 0.0402. Min Range: -0.0402

Max Act: 0.0305. Min Act: -0.0002

Data Index: 1145825 (C4 (Web Text))

Max Activating Token Index: 112

Text #5

Max Range: 0.0402. Min Range: -0.0402

Max Act: 0.0307. Min Act: -0.0002

Data Index: 237868 (C4 (Web Text))

Max Activating Token Index: 34

Text #6

Max Range: 0.0402. Min Range: -0.0402

Max Act: 0.0303. Min Act: -0.0002

Data Index: 476699 (C4 (Web Text))

Max Activating Token Index: 170

Text #7

Max Range: 0.0402. Min Range: -0.0402

Max Act: 0.0306. Min Act: -0.0002

Data Index: 380290 (C4 (Web Text))

Max Activating Token Index: 234

Text #8

Max Range: 0.0402. Min Range: -0.0402

Max Act: 0.0301. Min Act: -0.0002

Data Index: 488275 (C4 (Web Text))

Max Activating Token Index: 542

Text #9

Max Range: 0.0402. Min Range: -0.0402

Max Act: 0.0279. Min Act: -0.0002

Data Index: 545794 (C4 (Web Text))

Max Activating Token Index: 847

Text #10

Max Range: 0.0402. Min Range: -0.0402

Max Act: 0.0292. Min Act: -0.0002

Data Index: 1272583 (C4 (Web Text))

Max Activating Token Index: 801

Text #11

Max Range: 0.0402. Min Range: -0.0402

Max Act: 0.0272. Min Act: -0.0002

Data Index: 260398 (C4 (Web Text))

Max Activating Token Index: 35

Text #12

Max Range: 0.0402. Min Range: -0.0402

Max Act: 0.0276. Min Act: -0.0002

Data Index: 198697 (C4 (Web Text))

Max Activating Token Index: 84

Text #13

Max Range: 0.0402. Min Range: -0.0402

Max Act: 0.0283. Min Act: -0.0002

Data Index: 1186106 (C4 (Web Text))

Max Activating Token Index: 897

Text #14

Max Range: 0.0402. Min Range: -0.0402

Max Act: 0.0273. Min Act: -0.0002

Data Index: 704634 (C4 (Web Text))

Max Activating Token Index: 91

Text #15

Max Range: 0.0402. Min Range: -0.0402

Max Act: 0.0278. Min Act: -0.0002

Data Index: 1221017 (C4 (Web Text))

Max Activating Token Index: 115

Text #16

Max Range: 0.0402. Min Range: -0.0402

Max Act: 0.0280. Min Act: -0.0002

Data Index: 942929 (C4 (Web Text))

Max Activating Token Index: 251

Text #17

Max Range: 0.0402. Min Range: -0.0402

Max Act: 0.0273. Min Act: -0.0002

Data Index: 634109 (C4 (Web Text))

Max Activating Token Index: 175

Text #18

Max Range: 0.0402. Min Range: -0.0402

Max Act: 0.0267. Min Act: -0.0002

Data Index: 1012548 (C4 (Web Text))

Max Activating Token Index: 205

Text #19

Max Range: 0.0402. Min Range: -0.0402

Max Act: 0.0276. Min Act: -0.0002

Data Index: 428664 (C4 (Web Text))

Max Activating Token Index: 764