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

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

Neuron 3442 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: 0.0342. Min Range: -0.0342

Max Act: 0.0342. Min Act: -0.0003

Data Index: 958554 (C4 (Web Text))

Max Activating Token Index: 615

Text #1

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0312. Min Act: -0.0003

Data Index: 776935 (C4 (Web Text))

Max Activating Token Index: 149

Text #2

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0309. Min Act: -0.0003

Data Index: 452759 (C4 (Web Text))

Max Activating Token Index: 306

Text #3

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0284. Min Act: -0.0003

Data Index: 90158 (C4 (Web Text))

Max Activating Token Index: 258

Text #4

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0279. Min Act: -0.0003

Data Index: 602689 (C4 (Web Text))

Max Activating Token Index: 199

Text #5

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0278. Min Act: -0.0003

Data Index: 976155 (C4 (Web Text))

Max Activating Token Index: 606

Text #6

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0278. Min Act: -0.0003

Data Index: 968000 (C4 (Web Text))

Max Activating Token Index: 186

Text #7

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0275. Min Act: -0.0003

Data Index: 161601 (C4 (Web Text))

Max Activating Token Index: 709

Text #8

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0273. Min Act: -0.0003

Data Index: 402935 (C4 (Web Text))

Max Activating Token Index: 650

Text #9

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0272. Min Act: -0.0003

Data Index: 827871 (C4 (Web Text))

Max Activating Token Index: 488

Text #10

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0272. Min Act: -0.0003

Data Index: 928623 (C4 (Web Text))

Max Activating Token Index: 346

Text #11

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0269. Min Act: -0.0003

Data Index: 990544 (C4 (Web Text))

Max Activating Token Index: 527

Text #12

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0264. Min Act: -0.0003

Data Index: 186584 (C4 (Web Text))

Max Activating Token Index: 257

Text #13

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0257. Min Act: -0.0003

Data Index: 1318522 (C4 (Web Text))

Max Activating Token Index: 704

Text #14

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0261. Min Act: -0.0003

Data Index: 394486 (C4 (Web Text))

Max Activating Token Index: 740

Text #15

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0258. Min Act: -0.0003

Data Index: 60309 (C4 (Web Text))

Max Activating Token Index: 931

Text #16

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0256. Min Act: -0.0003

Data Index: 14997 (C4 (Web Text))

Max Activating Token Index: 434

Text #17

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0253. Min Act: -0.0003

Data Index: 311858 (C4 (Web Text))

Max Activating Token Index: 810

Text #18

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0251. Min Act: -0.0003

Data Index: 366535 (C4 (Web Text))

Max Activating Token Index: 301

Text #19

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0251. Min Act: -0.0003

Data Index: 325540 (C4 (Web Text))

Max Activating Token Index: 19