Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1369 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0439. Min Act: -0.0003

Data Index: 1107121 (C4 (Web Text))

Max Activating Token Index: 296

Text #1

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0403. Min Act: -0.0003

Data Index: 429574 (C4 (Web Text))

Max Activating Token Index: 394

Text #2

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0386. Min Act: -0.0003

Data Index: 1276449 (C4 (Web Text))

Max Activating Token Index: 192

Text #3

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0373. Min Act: -0.0003

Data Index: 363031 (C4 (Web Text))

Max Activating Token Index: 981

Text #4

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0339. Min Act: -0.0003

Data Index: 731786 (C4 (Web Text))

Max Activating Token Index: 95

Text #5

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0341. Min Act: -0.0002

Data Index: 1357017 (C4 (Web Text))

Max Activating Token Index: 250

Text #6

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0336. Min Act: -0.0002

Data Index: 1622484 (Python Code)

Max Activating Token Index: 764

Text #7

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0330. Min Act: -0.0003

Data Index: 166920 (C4 (Web Text))

Max Activating Token Index: 635

Text #8

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0318. Min Act: -0.0003

Data Index: 432894 (C4 (Web Text))

Max Activating Token Index: 719

Text #9

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0306. Min Act: -0.0003

Data Index: 740247 (C4 (Web Text))

Max Activating Token Index: 747

Text #10

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0314. Min Act: -0.0003

Data Index: 940360 (C4 (Web Text))

Max Activating Token Index: 595

Text #11

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0304. Min Act: -0.0003

Data Index: 1458886 (Python Code)

Max Activating Token Index: 375

Text #12

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0301. Min Act: -0.0003

Data Index: 896449 (C4 (Web Text))

Max Activating Token Index: 157

Text #13

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0299. Min Act: -0.0003

Data Index: 1548760 (Python Code)

Max Activating Token Index: 452

Text #14

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0314. Min Act: -0.0003

Data Index: 94354 (C4 (Web Text))

Max Activating Token Index: 662

Text #15

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0309. Min Act: -0.0003

Data Index: 401608 (C4 (Web Text))

Max Activating Token Index: 658

Text #16

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0304. Min Act: -0.0003

Data Index: 564379 (C4 (Web Text))

Max Activating Token Index: 527

Text #17

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0303. Min Act: -0.0003

Data Index: 132801 (C4 (Web Text))

Max Activating Token Index: 939

Text #18

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0300. Min Act: -0.0002

Data Index: 1555500 (Python Code)

Max Activating Token Index: 664

Text #19

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0288. Min Act: -0.0003

Data Index: 1194823 (C4 (Web Text))

Max Activating Token Index: 1012