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

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

Neuron 1648 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: 0.0396. Min Range: -0.0396

Max Act: 0.0396. Min Act: -0.0003

Data Index: 828681 (C4 (Web Text))

Max Activating Token Index: 238

Text #1

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0375. Min Act: -0.0003

Data Index: 1183782 (C4 (Web Text))

Max Activating Token Index: 116

Text #2

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0314. Min Act: -0.0003

Data Index: 802812 (C4 (Web Text))

Max Activating Token Index: 351

Text #3

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0323. Min Act: -0.0003

Data Index: 940452 (C4 (Web Text))

Max Activating Token Index: 136

Text #4

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0317. Min Act: -0.0003

Data Index: 1189402 (C4 (Web Text))

Max Activating Token Index: 565

Text #5

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0304. Min Act: -0.0003

Data Index: 1179927 (C4 (Web Text))

Max Activating Token Index: 159

Text #6

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0302. Min Act: -0.0003

Data Index: 911143 (C4 (Web Text))

Max Activating Token Index: 507

Text #7

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0292. Min Act: -0.0003

Data Index: 1246688 (C4 (Web Text))

Max Activating Token Index: 200

Text #8

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0299. Min Act: -0.0003

Data Index: 1092938 (C4 (Web Text))

Max Activating Token Index: 680

Text #9

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0297. Min Act: -0.0003

Data Index: 865491 (C4 (Web Text))

Max Activating Token Index: 270

Text #10

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0291. Min Act: -0.0002

Data Index: 1067804 (C4 (Web Text))

Max Activating Token Index: 172

Text #11

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0293. Min Act: -0.0003

Data Index: 600835 (C4 (Web Text))

Max Activating Token Index: 386

Text #12

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0288. Min Act: -0.0003

Data Index: 835898 (C4 (Web Text))

Max Activating Token Index: 111

Text #13

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0282. Min Act: -0.0003

Data Index: 23148 (C4 (Web Text))

Max Activating Token Index: 368

Text #14

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0277. Min Act: -0.0003

Data Index: 213847 (C4 (Web Text))

Max Activating Token Index: 499

Text #15

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0273. Min Act: -0.0003

Data Index: 1030618 (C4 (Web Text))

Max Activating Token Index: 707

Text #16

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0285. Min Act: -0.0003

Data Index: 802482 (C4 (Web Text))

Max Activating Token Index: 426

Text #17

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0281. Min Act: -0.0002

Data Index: 1110936 (C4 (Web Text))

Max Activating Token Index: 285

Text #18

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0280. Min Act: -0.0003

Data Index: 273789 (C4 (Web Text))

Max Activating Token Index: 636

Text #19

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0271. Min Act: -0.0003

Data Index: 118827 (C4 (Web Text))

Max Activating Token Index: 279