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

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

Neuron 387 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: 0.0306. Min Range: -0.0306

Max Act: 0.0306. Min Act: -0.0003

Data Index: 1398984 (Python Code)

Max Activating Token Index: 420

Text #1

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0288. Min Act: -0.0003

Data Index: 1636713 (Python Code)

Max Activating Token Index: 792

Text #2

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0280. Min Act: -0.0004

Data Index: 332042 (C4 (Web Text))

Max Activating Token Index: 648

Text #3

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0281. Min Act: -0.0003

Data Index: 730684 (C4 (Web Text))

Max Activating Token Index: 466

Text #4

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0275. Min Act: -0.0003

Data Index: 1581836 (Python Code)

Max Activating Token Index: 96

Text #5

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0264. Min Act: -0.0003

Data Index: 611252 (C4 (Web Text))

Max Activating Token Index: 649

Text #6

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0266. Min Act: -0.0003

Data Index: 723905 (C4 (Web Text))

Max Activating Token Index: 48

Text #7

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0265. Min Act: -0.0003

Data Index: 402184 (C4 (Web Text))

Max Activating Token Index: 426

Text #8

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0264. Min Act: -0.0003

Data Index: 1402743 (Python Code)

Max Activating Token Index: 196

Text #9

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0249. Min Act: -0.0003

Data Index: 1651457 (Python Code)

Max Activating Token Index: 792

Text #10

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0245. Min Act: -0.0002

Data Index: 1542262 (Python Code)

Max Activating Token Index: 549

Text #11

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0252. Min Act: -0.0003

Data Index: 698397 (C4 (Web Text))

Max Activating Token Index: 558

Text #12

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0235. Min Act: -0.0003

Data Index: 366764 (C4 (Web Text))

Max Activating Token Index: 45

Text #13

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0243. Min Act: -0.0002

Data Index: 1560338 (Python Code)

Max Activating Token Index: 298

Text #14

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0251. Min Act: -0.0002

Data Index: 1535914 (Python Code)

Max Activating Token Index: 471

Text #15

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0235. Min Act: -0.0003

Data Index: 726341 (C4 (Web Text))

Max Activating Token Index: 436

Text #16

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0232. Min Act: -0.0003

Data Index: 191793 (C4 (Web Text))

Max Activating Token Index: 741

Text #17

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0235. Min Act: -0.0003

Data Index: 1563415 (Python Code)

Max Activating Token Index: 958

Text #18

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0240. Min Act: -0.0003

Data Index: 1404974 (Python Code)

Max Activating Token Index: 388

Text #19

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0242. Min Act: -0.0003

Data Index: 1507276 (Python Code)

Max Activating Token Index: 590