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

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

Neuron 442 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: 0.0327. Min Range: -0.0327

Max Act: 0.0325. Min Act: -0.0002

Data Index: 294715 (C4 (Web Text))

Max Activating Token Index: 431

Text #1

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0327. Min Act: -0.0002

Data Index: 1544002 (Python Code)

Max Activating Token Index: 6

Text #2

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0297. Min Act: -0.0002

Data Index: 306712 (C4 (Web Text))

Max Activating Token Index: 795

Text #3

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0294. Min Act: -0.0002

Data Index: 15368 (C4 (Web Text))

Max Activating Token Index: 601

Text #4

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0296. Min Act: -0.0002

Data Index: 415147 (C4 (Web Text))

Max Activating Token Index: 646

Text #5

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0291. Min Act: -0.0002

Data Index: 780940 (C4 (Web Text))

Max Activating Token Index: 275

Text #6

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0290. Min Act: -0.0002

Data Index: 1022683 (C4 (Web Text))

Max Activating Token Index: 266

Text #7

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0284. Min Act: -0.0002

Data Index: 89408 (C4 (Web Text))

Max Activating Token Index: 296

Text #8

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0284. Min Act: -0.0002

Data Index: 1440251 (Python Code)

Max Activating Token Index: 240

Text #9

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0276. Min Act: -0.0002

Data Index: 1351487 (C4 (Web Text))

Max Activating Token Index: 623

Text #10

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0281. Min Act: -0.0002

Data Index: 420970 (C4 (Web Text))

Max Activating Token Index: 628

Text #11

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0267. Min Act: -0.0002

Data Index: 1322204 (C4 (Web Text))

Max Activating Token Index: 692

Text #12

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0278. Min Act: -0.0002

Data Index: 1218745 (C4 (Web Text))

Max Activating Token Index: 28

Text #13

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0265. Min Act: -0.0002

Data Index: 380544 (C4 (Web Text))

Max Activating Token Index: 305

Text #14

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0276. Min Act: -0.0002

Data Index: 49924 (C4 (Web Text))

Max Activating Token Index: 452

Text #15

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0263. Min Act: -0.0002

Data Index: 843338 (C4 (Web Text))

Max Activating Token Index: 209

Text #16

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0262. Min Act: -0.0002

Data Index: 285456 (C4 (Web Text))

Max Activating Token Index: 390

Text #17

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0264. Min Act: -0.0002

Data Index: 1487554 (Python Code)

Max Activating Token Index: 658

Text #18

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0258. Min Act: -0.0002

Data Index: 622030 (C4 (Web Text))

Max Activating Token Index: 22

Text #19

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0266. Min Act: -0.0002

Data Index: 212671 (C4 (Web Text))

Max Activating Token Index: 293