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

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

Neuron 2062 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3548. Min Range: -0.3548

Max Act: 0.3548. Min Act: 0.0000

Data Index: 20297 (C4 (Web Text))

Max Activating Token Index: 710

Text #1

Max Range: 0.3548. Min Range: -0.3548

Max Act: 0.3270. Min Act: 0.0000

Data Index: 413515 (C4 (Web Text))

Max Activating Token Index: 500

Text #2

Max Range: 0.3548. Min Range: -0.3548

Max Act: 0.3117. Min Act: -0.0000

Data Index: 341203 (C4 (Web Text))

Max Activating Token Index: 447

Text #3

Max Range: 0.3548. Min Range: -0.3548

Max Act: 0.2938. Min Act: -0.0000

Data Index: 759010 (C4 (Web Text))

Max Activating Token Index: 714

Text #4

Max Range: 0.3548. Min Range: -0.3548

Max Act: 0.2719. Min Act: -0.0000

Data Index: 134596 (C4 (Web Text))

Max Activating Token Index: 363

Text #5

Max Range: 0.3548. Min Range: -0.3548

Max Act: 0.2641. Min Act: 0.0000

Data Index: 169384 (C4 (Web Text))

Max Activating Token Index: 27

Text #6

Max Range: 0.3548. Min Range: -0.3548

Max Act: 0.2374. Min Act: -0.0000

Data Index: 215077 (C4 (Web Text))

Max Activating Token Index: 259

Text #7

Max Range: 0.3548. Min Range: -0.3548

Max Act: 0.2434. Min Act: -0.0000

Data Index: 84703 (C4 (Web Text))

Max Activating Token Index: 493

Text #8

Max Range: 0.3548. Min Range: -0.3548

Max Act: 0.2359. Min Act: -0.0000

Data Index: 234711 (C4 (Web Text))

Max Activating Token Index: 891

Text #9

Max Range: 0.3548. Min Range: -0.3548

Max Act: 0.2489. Min Act: -0.0000

Data Index: 513605 (C4 (Web Text))

Max Activating Token Index: 752

Text #10

Max Range: 0.3548. Min Range: -0.3548

Max Act: 0.2323. Min Act: 0.0000

Data Index: 1148144 (C4 (Web Text))

Max Activating Token Index: 429

Text #11

Max Range: 0.3548. Min Range: -0.3548

Max Act: 0.2294. Min Act: -0.0000

Data Index: 421625 (C4 (Web Text))

Max Activating Token Index: 791

Text #12

Max Range: 0.3548. Min Range: -0.3548

Max Act: 0.2357. Min Act: -0.0000

Data Index: 795263 (C4 (Web Text))

Max Activating Token Index: 792

Text #13

Max Range: 0.3548. Min Range: -0.3548

Max Act: 0.2368. Min Act: -0.0000

Data Index: 459029 (C4 (Web Text))

Max Activating Token Index: 750

Text #14

Max Range: 0.3548. Min Range: -0.3548

Max Act: 0.2310. Min Act: -0.0000

Data Index: 115077 (C4 (Web Text))

Max Activating Token Index: 902

Text #15

Max Range: 0.3548. Min Range: -0.3548

Max Act: 0.2257. Min Act: -0.0000

Data Index: 424884 (C4 (Web Text))

Max Activating Token Index: 809

Text #16

Max Range: 0.3548. Min Range: -0.3548

Max Act: 0.2337. Min Act: -0.0000

Data Index: 404477 (C4 (Web Text))

Max Activating Token Index: 939

Text #17

Max Range: 0.3548. Min Range: -0.3548

Max Act: 0.2627. Min Act: -0.0000

Data Index: 51760 (C4 (Web Text))

Max Activating Token Index: 712

Text #18

Max Range: 0.3548. Min Range: -0.3548

Max Act: 0.2371. Min Act: -0.0000

Data Index: 1129215 (C4 (Web Text))

Max Activating Token Index: 499

Text #19

Max Range: 0.3548. Min Range: -0.3548

Max Act: 0.2271. Min Act: -0.0000

Data Index: 713176 (C4 (Web Text))

Max Activating Token Index: 94