Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1150 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0367. Min Act: -0.0002

Data Index: 1012945 (C4 (Web Text))

Max Activating Token Index: 754

Text #1

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0316. Min Act: -0.0002

Data Index: 1332524 (C4 (Web Text))

Max Activating Token Index: 279

Text #2

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0317. Min Act: -0.0002

Data Index: 716586 (C4 (Web Text))

Max Activating Token Index: 330

Text #3

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0295. Min Act: -0.0002

Data Index: 624508 (C4 (Web Text))

Max Activating Token Index: 180

Text #4

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0370. Min Act: -0.0002

Data Index: 982571 (C4 (Web Text))

Max Activating Token Index: 736

Text #5

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0275. Min Act: -0.0002

Data Index: 583848 (C4 (Web Text))

Max Activating Token Index: 928

Text #6

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0273. Min Act: -0.0002

Data Index: 238125 (C4 (Web Text))

Max Activating Token Index: 945

Text #7

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0290. Min Act: -0.0002

Data Index: 200269 (C4 (Web Text))

Max Activating Token Index: 757

Text #8

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0273. Min Act: -0.0002

Data Index: 708852 (C4 (Web Text))

Max Activating Token Index: 5

Text #9

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0268. Min Act: -0.0002

Data Index: 602444 (C4 (Web Text))

Max Activating Token Index: 259

Text #10

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0267. Min Act: -0.0002

Data Index: 26035 (C4 (Web Text))

Max Activating Token Index: 948

Text #11

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0263. Min Act: -0.0002

Data Index: 1077872 (C4 (Web Text))

Max Activating Token Index: 63

Text #12

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0279. Min Act: -0.0002

Data Index: 1467953 (Python Code)

Max Activating Token Index: 50

Text #13

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0274. Min Act: -0.0002

Data Index: 100197 (C4 (Web Text))

Max Activating Token Index: 232

Text #14

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0278. Min Act: -0.0002

Data Index: 1033656 (C4 (Web Text))

Max Activating Token Index: 308

Text #15

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0258. Min Act: -0.0002

Data Index: 622003 (C4 (Web Text))

Max Activating Token Index: 233

Text #16

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0223. Min Act: -0.0002

Data Index: 718338 (C4 (Web Text))

Max Activating Token Index: 236

Text #17

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0314. Min Act: -0.0002

Data Index: 867568 (C4 (Web Text))

Max Activating Token Index: 723

Text #18

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0276. Min Act: -0.0002

Data Index: 1423762 (Python Code)

Max Activating Token Index: 853

Text #19

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0262. Min Act: -0.0002

Data Index: 272282 (C4 (Web Text))

Max Activating Token Index: 944