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

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

Neuron 2472 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: 0.0418. Min Range: -0.0418

Max Act: 0.0418. Min Act: -0.0002

Data Index: 1150592 (C4 (Web Text))

Max Activating Token Index: 873

Text #1

Max Range: 0.0418. Min Range: -0.0418

Max Act: 0.0394. Min Act: -0.0002

Data Index: 811373 (C4 (Web Text))

Max Activating Token Index: 109

Text #2

Max Range: 0.0418. Min Range: -0.0418

Max Act: 0.0411. Min Act: -0.0002

Data Index: 624429 (C4 (Web Text))

Max Activating Token Index: 621

Text #3

Max Range: 0.0418. Min Range: -0.0418

Max Act: 0.0355. Min Act: -0.0002

Data Index: 992267 (C4 (Web Text))

Max Activating Token Index: 999

Text #4

Max Range: 0.0418. Min Range: -0.0418

Max Act: 0.0342. Min Act: -0.0002

Data Index: 500087 (C4 (Web Text))

Max Activating Token Index: 402

Text #5

Max Range: 0.0418. Min Range: -0.0418

Max Act: 0.0312. Min Act: -0.0002

Data Index: 1286010 (C4 (Web Text))

Max Activating Token Index: 180

Text #6

Max Range: 0.0418. Min Range: -0.0418

Max Act: 0.0305. Min Act: -0.0002

Data Index: 205345 (C4 (Web Text))

Max Activating Token Index: 121

Text #7

Max Range: 0.0418. Min Range: -0.0418

Max Act: 0.0288. Min Act: -0.0002

Data Index: 329238 (C4 (Web Text))

Max Activating Token Index: 859

Text #8

Max Range: 0.0418. Min Range: -0.0418

Max Act: 0.0291. Min Act: -0.0003

Data Index: 177260 (C4 (Web Text))

Max Activating Token Index: 852

Text #9

Max Range: 0.0418. Min Range: -0.0418

Max Act: 0.0290. Min Act: -0.0002

Data Index: 630099 (C4 (Web Text))

Max Activating Token Index: 660

Text #10

Max Range: 0.0418. Min Range: -0.0418

Max Act: 0.0277. Min Act: -0.0002

Data Index: 230975 (C4 (Web Text))

Max Activating Token Index: 644

Text #11

Max Range: 0.0418. Min Range: -0.0418

Max Act: 0.0288. Min Act: -0.0002

Data Index: 490186 (C4 (Web Text))

Max Activating Token Index: 980

Text #12

Max Range: 0.0418. Min Range: -0.0418

Max Act: 0.0283. Min Act: -0.0002

Data Index: 664807 (C4 (Web Text))

Max Activating Token Index: 533

Text #13

Max Range: 0.0418. Min Range: -0.0418

Max Act: 0.0280. Min Act: -0.0002

Data Index: 905197 (C4 (Web Text))

Max Activating Token Index: 957

Text #14

Max Range: 0.0418. Min Range: -0.0418

Max Act: 0.0267. Min Act: -0.0002

Data Index: 1285850 (C4 (Web Text))

Max Activating Token Index: 680

Text #15

Max Range: 0.0418. Min Range: -0.0418

Max Act: 0.0258. Min Act: -0.0002

Data Index: 1296045 (C4 (Web Text))

Max Activating Token Index: 715

Text #16

Max Range: 0.0418. Min Range: -0.0418

Max Act: 0.0264. Min Act: -0.0002

Data Index: 426015 (C4 (Web Text))

Max Activating Token Index: 940

Text #17

Max Range: 0.0418. Min Range: -0.0418

Max Act: 0.0255. Min Act: -0.0002

Data Index: 122335 (C4 (Web Text))

Max Activating Token Index: 723

Text #18

Max Range: 0.0418. Min Range: -0.0418

Max Act: 0.0246. Min Act: -0.0002

Data Index: 1312927 (C4 (Web Text))

Max Activating Token Index: 710

Text #19

Max Range: 0.0418. Min Range: -0.0418

Max Act: 0.0253. Min Act: -0.0002

Data Index: 625136 (C4 (Web Text))

Max Activating Token Index: 922