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

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

Neuron 4608 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: 0.0247. Min Range: -0.0247

Max Act: 0.0242. Min Act: -0.0003

Data Index: 305078 (C4 (Web Text))

Max Activating Token Index: 285

Text #1

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0231. Min Act: -0.0003

Data Index: 27028 (C4 (Web Text))

Max Activating Token Index: 735

Text #2

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0247. Min Act: -0.0003

Data Index: 916279 (C4 (Web Text))

Max Activating Token Index: 783

Text #3

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0220. Min Act: -0.0003

Data Index: 723345 (C4 (Web Text))

Max Activating Token Index: 271

Text #4

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0210. Min Act: -0.0002

Data Index: 149229 (C4 (Web Text))

Max Activating Token Index: 702

Text #5

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0223. Min Act: -0.0003

Data Index: 819062 (C4 (Web Text))

Max Activating Token Index: 822

Text #6

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0210. Min Act: -0.0003

Data Index: 858721 (C4 (Web Text))

Max Activating Token Index: 657

Text #7

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0205. Min Act: -0.0002

Data Index: 1286254 (C4 (Web Text))

Max Activating Token Index: 98

Text #8

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0194. Min Act: -0.0003

Data Index: 90013 (C4 (Web Text))

Max Activating Token Index: 745

Text #9

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0187. Min Act: -0.0003

Data Index: 411161 (C4 (Web Text))

Max Activating Token Index: 154

Text #10

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0195. Min Act: -0.0003

Data Index: 1285411 (C4 (Web Text))

Max Activating Token Index: 866

Text #11

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0192. Min Act: -0.0003

Data Index: 824707 (C4 (Web Text))

Max Activating Token Index: 600

Text #12

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0203. Min Act: -0.0003

Data Index: 727210 (C4 (Web Text))

Max Activating Token Index: 388

Text #13

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0190. Min Act: -0.0003

Data Index: 448658 (C4 (Web Text))

Max Activating Token Index: 283

Text #14

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0188. Min Act: -0.0003

Data Index: 1109288 (C4 (Web Text))

Max Activating Token Index: 293

Text #15

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0190. Min Act: -0.0003

Data Index: 1075458 (C4 (Web Text))

Max Activating Token Index: 204

Text #16

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0199. Min Act: -0.0003

Data Index: 1087364 (C4 (Web Text))

Max Activating Token Index: 681

Text #17

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0190. Min Act: -0.0002

Data Index: 643786 (C4 (Web Text))

Max Activating Token Index: 641

Text #18

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0185. Min Act: -0.0002

Data Index: 273640 (C4 (Web Text))

Max Activating Token Index: 228

Text #19

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0191. Min Act: -0.0003

Data Index: 1235789 (C4 (Web Text))

Max Activating Token Index: 830