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

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

Neuron 3976 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: 0.0271. Min Range: -0.0271

Max Act: 0.0271. Min Act: -0.0003

Data Index: 1364901 (Python Code)

Max Activating Token Index: 767

Text #1

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0249. Min Act: -0.0003

Data Index: 637071 (C4 (Web Text))

Max Activating Token Index: 233

Text #2

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0241. Min Act: -0.0003

Data Index: 441388 (C4 (Web Text))

Max Activating Token Index: 775

Text #3

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0238. Min Act: -0.0003

Data Index: 1013684 (C4 (Web Text))

Max Activating Token Index: 410

Text #4

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0225. Min Act: -0.0003

Data Index: 1647131 (Python Code)

Max Activating Token Index: 563

Text #5

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0203. Min Act: -0.0003

Data Index: 9911 (C4 (Web Text))

Max Activating Token Index: 334

Text #6

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0213. Min Act: -0.0003

Data Index: 824376 (C4 (Web Text))

Max Activating Token Index: 249

Text #7

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0205. Min Act: -0.0003

Data Index: 571486 (C4 (Web Text))

Max Activating Token Index: 220

Text #8

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0205. Min Act: -0.0002

Data Index: 47748 (C4 (Web Text))

Max Activating Token Index: 182

Text #9

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0199. Min Act: -0.0003

Data Index: 863301 (C4 (Web Text))

Max Activating Token Index: 225

Text #10

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0213. Min Act: -0.0003

Data Index: 480021 (C4 (Web Text))

Max Activating Token Index: 920

Text #11

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0199. Min Act: -0.0003

Data Index: 197508 (C4 (Web Text))

Max Activating Token Index: 237

Text #12

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0215. Min Act: -0.0003

Data Index: 851962 (C4 (Web Text))

Max Activating Token Index: 119

Text #13

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0205. Min Act: -0.0003

Data Index: 1057746 (C4 (Web Text))

Max Activating Token Index: 701

Text #14

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0199. Min Act: -0.0003

Data Index: 750031 (C4 (Web Text))

Max Activating Token Index: 15

Text #15

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0206. Min Act: -0.0003

Data Index: 175914 (C4 (Web Text))

Max Activating Token Index: 509

Text #16

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0200. Min Act: -0.0003

Data Index: 1382466 (Python Code)

Max Activating Token Index: 469

Text #17

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0206. Min Act: -0.0003

Data Index: 490513 (C4 (Web Text))

Max Activating Token Index: 902

Text #18

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0209. Min Act: -0.0003

Data Index: 97475 (C4 (Web Text))

Max Activating Token Index: 837

Text #19

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0191. Min Act: -0.0003

Data Index: 880797 (C4 (Web Text))

Max Activating Token Index: 784