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

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

Neuron 5750 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: 0.0461. Min Range: -0.0461

Max Act: 0.0461. Min Act: -0.0002

Data Index: 748853 (C4 (Web Text))

Max Activating Token Index: 893

Text #1

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0355. Min Act: -0.0002

Data Index: 793651 (C4 (Web Text))

Max Activating Token Index: 95

Text #2

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0341. Min Act: -0.0002

Data Index: 977312 (C4 (Web Text))

Max Activating Token Index: 199

Text #3

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0332. Min Act: -0.0002

Data Index: 608216 (C4 (Web Text))

Max Activating Token Index: 676

Text #4

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0327. Min Act: -0.0002

Data Index: 391434 (C4 (Web Text))

Max Activating Token Index: 224

Text #5

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0324. Min Act: -0.0002

Data Index: 1339335 (C4 (Web Text))

Max Activating Token Index: 865

Text #6

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0330. Min Act: -0.0002

Data Index: 994366 (C4 (Web Text))

Max Activating Token Index: 148

Text #7

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0330. Min Act: -0.0002

Data Index: 859586 (C4 (Web Text))

Max Activating Token Index: 81

Text #8

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0313. Min Act: -0.0002

Data Index: 1110869 (C4 (Web Text))

Max Activating Token Index: 808

Text #9

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0308. Min Act: -0.0002

Data Index: 101724 (C4 (Web Text))

Max Activating Token Index: 700

Text #10

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0303. Min Act: -0.0002

Data Index: 457130 (C4 (Web Text))

Max Activating Token Index: 489

Text #11

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0324. Min Act: -0.0002

Data Index: 619967 (C4 (Web Text))

Max Activating Token Index: 793

Text #12

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0301. Min Act: -0.0002

Data Index: 1181054 (C4 (Web Text))

Max Activating Token Index: 43

Text #13

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0295. Min Act: -0.0002

Data Index: 936225 (C4 (Web Text))

Max Activating Token Index: 892

Text #14

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0284. Min Act: -0.0002

Data Index: 960437 (C4 (Web Text))

Max Activating Token Index: 89

Text #15

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0265. Min Act: -0.0002

Data Index: 741251 (C4 (Web Text))

Max Activating Token Index: 328

Text #16

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0286. Min Act: -0.0002

Data Index: 8159 (C4 (Web Text))

Max Activating Token Index: 761

Text #17

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0297. Min Act: -0.0002

Data Index: 192553 (C4 (Web Text))

Max Activating Token Index: 387

Text #18

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0282. Min Act: -0.0002

Data Index: 152569 (C4 (Web Text))

Max Activating Token Index: 765

Text #19

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0287. Min Act: -0.0002

Data Index: 863286 (C4 (Web Text))

Max Activating Token Index: 97