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

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

Neuron 4830 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: 0.0307. Min Range: -0.0307

Max Act: 0.0307. Min Act: -0.0003

Data Index: 426015 (C4 (Web Text))

Max Activating Token Index: 940

Text #1

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0286. Min Act: -0.0002

Data Index: 266053 (C4 (Web Text))

Max Activating Token Index: 680

Text #2

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0263. Min Act: -0.0002

Data Index: 1291519 (C4 (Web Text))

Max Activating Token Index: 651

Text #3

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0267. Min Act: -0.0003

Data Index: 361374 (C4 (Web Text))

Max Activating Token Index: 964

Text #4

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0253. Min Act: -0.0002

Data Index: 809044 (C4 (Web Text))

Max Activating Token Index: 74

Text #5

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0236. Min Act: -0.0002

Data Index: 858390 (C4 (Web Text))

Max Activating Token Index: 519

Text #6

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0233. Min Act: -0.0002

Data Index: 844565 (C4 (Web Text))

Max Activating Token Index: 353

Text #7

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0234. Min Act: -0.0002

Data Index: 1038499 (C4 (Web Text))

Max Activating Token Index: 42

Text #8

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0224. Min Act: -0.0003

Data Index: 38298 (C4 (Web Text))

Max Activating Token Index: 259

Text #9

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0221. Min Act: -0.0003

Data Index: 904341 (C4 (Web Text))

Max Activating Token Index: 139

Text #10

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0223. Min Act: -0.0002

Data Index: 576937 (C4 (Web Text))

Max Activating Token Index: 648

Text #11

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0211. Min Act: -0.0002

Data Index: 1207904 (C4 (Web Text))

Max Activating Token Index: 607

Text #12

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0210. Min Act: -0.0002

Data Index: 517803 (C4 (Web Text))

Max Activating Token Index: 95

Text #13

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0201. Min Act: -0.0002

Data Index: 897710 (C4 (Web Text))

Max Activating Token Index: 769

Text #14

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0198. Min Act: -0.0003

Data Index: 481901 (C4 (Web Text))

Max Activating Token Index: 352

Text #15

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0208. Min Act: -0.0003

Data Index: 596643 (C4 (Web Text))

Max Activating Token Index: 944

Text #16

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0201. Min Act: -0.0003

Data Index: 962865 (C4 (Web Text))

Max Activating Token Index: 791

Text #17

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0191. Min Act: -0.0002

Data Index: 400156 (C4 (Web Text))

Max Activating Token Index: 303

Text #18

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0194. Min Act: -0.0002

Data Index: 323140 (C4 (Web Text))

Max Activating Token Index: 907

Text #19

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0184. Min Act: -0.0002

Data Index: 366437 (C4 (Web Text))

Max Activating Token Index: 232