Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 161 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0271. Min Act: -0.0006

Data Index: 1054260 (C4 (Web Text))

Max Activating Token Index: 637

Text #1

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0263. Min Act: -0.0006

Data Index: 299494 (C4 (Web Text))

Max Activating Token Index: 576

Text #2

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0262. Min Act: -0.0006

Data Index: 1073183 (C4 (Web Text))

Max Activating Token Index: 906

Text #3

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0260. Min Act: -0.0006

Data Index: 111365 (C4 (Web Text))

Max Activating Token Index: 496

Text #4

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0239. Min Act: -0.0006

Data Index: 786973 (C4 (Web Text))

Max Activating Token Index: 912

Text #5

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0265. Min Act: -0.0006

Data Index: 986517 (C4 (Web Text))

Max Activating Token Index: 721

Text #6

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0236. Min Act: -0.0006

Data Index: 338722 (C4 (Web Text))

Max Activating Token Index: 738

Text #7

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0250. Min Act: -0.0006

Data Index: 218570 (C4 (Web Text))

Max Activating Token Index: 240

Text #8

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0238. Min Act: -0.0006

Data Index: 1103750 (C4 (Web Text))

Max Activating Token Index: 275

Text #9

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0243. Min Act: -0.0006

Data Index: 324661 (C4 (Web Text))

Max Activating Token Index: 932

Text #10

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0242. Min Act: -0.0006

Data Index: 1116662 (C4 (Web Text))

Max Activating Token Index: 244

Text #11

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0238. Min Act: -0.0006

Data Index: 68687 (C4 (Web Text))

Max Activating Token Index: 674

Text #12

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0244. Min Act: -0.0006

Data Index: 376207 (C4 (Web Text))

Max Activating Token Index: 589

Text #13

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0233. Min Act: -0.0006

Data Index: 814397 (C4 (Web Text))

Max Activating Token Index: 338

Text #14

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0236. Min Act: -0.0006

Data Index: 1389603 (Python Code)

Max Activating Token Index: 15

Text #15

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0225. Min Act: -0.0006

Data Index: 1251640 (C4 (Web Text))

Max Activating Token Index: 179

Text #16

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0222. Min Act: -0.0006

Data Index: 218915 (C4 (Web Text))

Max Activating Token Index: 769

Text #17

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0221. Min Act: -0.0006

Data Index: 385349 (C4 (Web Text))

Max Activating Token Index: 763

Text #18

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0223. Min Act: -0.0006

Data Index: 453914 (C4 (Web Text))

Max Activating Token Index: 777

Text #19

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0217. Min Act: -0.0006

Data Index: 1000338 (C4 (Web Text))

Max Activating Token Index: 341