Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3434 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0466. Min Act: -0.0003

Data Index: 532199 (C4 (Web Text))

Max Activating Token Index: 465

Text #1

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0398. Min Act: -0.0003

Data Index: 308583 (C4 (Web Text))

Max Activating Token Index: 346

Text #2

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0388. Min Act: -0.0003

Data Index: 272774 (C4 (Web Text))

Max Activating Token Index: 83

Text #3

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0385. Min Act: -0.0002

Data Index: 551651 (C4 (Web Text))

Max Activating Token Index: 722

Text #4

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0345. Min Act: -0.0002

Data Index: 400778 (C4 (Web Text))

Max Activating Token Index: 524

Text #5

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0329. Min Act: -0.0003

Data Index: 828414 (C4 (Web Text))

Max Activating Token Index: 579

Text #6

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0317. Min Act: -0.0003

Data Index: 1280582 (C4 (Web Text))

Max Activating Token Index: 768

Text #7

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0292. Min Act: -0.0003

Data Index: 730391 (C4 (Web Text))

Max Activating Token Index: 82

Text #8

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0283. Min Act: -0.0003

Data Index: 735706 (C4 (Web Text))

Max Activating Token Index: 397

Text #9

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0285. Min Act: -0.0002

Data Index: 1553119 (Python Code)

Max Activating Token Index: 189

Text #10

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0285. Min Act: -0.0002

Data Index: 560931 (C4 (Web Text))

Max Activating Token Index: 66

Text #11

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0279. Min Act: -0.0003

Data Index: 860723 (C4 (Web Text))

Max Activating Token Index: 792

Text #12

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0273. Min Act: -0.0003

Data Index: 1033662 (C4 (Web Text))

Max Activating Token Index: 873

Text #13

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0274. Min Act: -0.0003

Data Index: 778393 (C4 (Web Text))

Max Activating Token Index: 1006

Text #14

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0270. Min Act: -0.0002

Data Index: 984032 (C4 (Web Text))

Max Activating Token Index: 130

Text #15

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0273. Min Act: -0.0003

Data Index: 1159695 (C4 (Web Text))

Max Activating Token Index: 686

Text #16

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0267. Min Act: -0.0000

Data Index: 159112 (C4 (Web Text))

Max Activating Token Index: 109

Text #17

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0266. Min Act: -0.0003

Data Index: 63536 (C4 (Web Text))

Max Activating Token Index: 37

Text #18

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0264. Min Act: -0.0002

Data Index: 16068 (C4 (Web Text))

Max Activating Token Index: 123

Text #19

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0262. Min Act: -0.0000

Data Index: 635219 (C4 (Web Text))

Max Activating Token Index: 91