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

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

Neuron 3642 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0324. Min Act: -0.0003

Data Index: 1622462 (Python Code)

Max Activating Token Index: 761

Text #1

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0291. Min Act: -0.0002

Data Index: 1148571 (C4 (Web Text))

Max Activating Token Index: 437

Text #2

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0298. Min Act: -0.0003

Data Index: 1021139 (C4 (Web Text))

Max Activating Token Index: 38

Text #3

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0305. Min Act: -0.0002

Data Index: 242126 (C4 (Web Text))

Max Activating Token Index: 717

Text #4

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0302. Min Act: -0.0002

Data Index: 1276050 (C4 (Web Text))

Max Activating Token Index: 474

Text #5

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0302. Min Act: -0.0002

Data Index: 583843 (C4 (Web Text))

Max Activating Token Index: 79

Text #6

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0282. Min Act: -0.0003

Data Index: 786424 (C4 (Web Text))

Max Activating Token Index: 518

Text #7

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0274. Min Act: -0.0003

Data Index: 1050469 (C4 (Web Text))

Max Activating Token Index: 185

Text #8

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0263. Min Act: -0.0003

Data Index: 1065248 (C4 (Web Text))

Max Activating Token Index: 607

Text #9

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0275. Min Act: -0.0002

Data Index: 234693 (C4 (Web Text))

Max Activating Token Index: 27

Text #10

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0294. Min Act: -0.0003

Data Index: 805056 (C4 (Web Text))

Max Activating Token Index: 717

Text #11

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0274. Min Act: -0.0002

Data Index: 1255926 (C4 (Web Text))

Max Activating Token Index: 507

Text #12

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0273. Min Act: -0.0002

Data Index: 1191629 (C4 (Web Text))

Max Activating Token Index: 301

Text #13

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0249. Min Act: -0.0003

Data Index: 917142 (C4 (Web Text))

Max Activating Token Index: 744

Text #14

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0260. Min Act: -0.0002

Data Index: 583452 (C4 (Web Text))

Max Activating Token Index: 852

Text #15

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0264. Min Act: -0.0003

Data Index: 503284 (C4 (Web Text))

Max Activating Token Index: 825

Text #16

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0270. Min Act: -0.0003

Data Index: 1594124 (Python Code)

Max Activating Token Index: 101

Text #17

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0242. Min Act: -0.0002

Data Index: 1010533 (C4 (Web Text))

Max Activating Token Index: 376

Text #18

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0263. Min Act: -0.0002

Data Index: 113558 (C4 (Web Text))

Max Activating Token Index: 45

Text #19

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0253. Min Act: -0.0003

Data Index: 1332114 (C4 (Web Text))

Max Activating Token Index: 841