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

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

Neuron 2988 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: 0.0284. Min Range: -0.0284

Max Act: 0.0279. Min Act: -0.0003

Data Index: 159475 (C4 (Web Text))

Max Activating Token Index: 265

Text #1

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0279. Min Act: -0.0003

Data Index: 1162206 (C4 (Web Text))

Max Activating Token Index: 748

Text #2

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0284. Min Act: -0.0003

Data Index: 75526 (C4 (Web Text))

Max Activating Token Index: 906

Text #3

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0271. Min Act: -0.0003

Data Index: 993665 (C4 (Web Text))

Max Activating Token Index: 408

Text #4

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0274. Min Act: -0.0003

Data Index: 718800 (C4 (Web Text))

Max Activating Token Index: 936

Text #5

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0255. Min Act: -0.0003

Data Index: 1358611 (C4 (Web Text))

Max Activating Token Index: 136

Text #6

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0248. Min Act: -0.0003

Data Index: 472876 (C4 (Web Text))

Max Activating Token Index: 60

Text #7

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0252. Min Act: -0.0003

Data Index: 1196809 (C4 (Web Text))

Max Activating Token Index: 68

Text #8

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0249. Min Act: -0.0003

Data Index: 1221180 (C4 (Web Text))

Max Activating Token Index: 603

Text #9

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0256. Min Act: -0.0003

Data Index: 976221 (C4 (Web Text))

Max Activating Token Index: 87

Text #10

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0248. Min Act: -0.0003

Data Index: 1204234 (C4 (Web Text))

Max Activating Token Index: 268

Text #11

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0246. Min Act: -0.0003

Data Index: 952893 (C4 (Web Text))

Max Activating Token Index: 724

Text #12

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0247. Min Act: -0.0002

Data Index: 117845 (C4 (Web Text))

Max Activating Token Index: 853

Text #13

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0241. Min Act: -0.0003

Data Index: 1645789 (Python Code)

Max Activating Token Index: 872

Text #14

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0246. Min Act: -0.0003

Data Index: 698690 (C4 (Web Text))

Max Activating Token Index: 353

Text #15

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0243. Min Act: -0.0002

Data Index: 250733 (C4 (Web Text))

Max Activating Token Index: 995

Text #16

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0243. Min Act: -0.0003

Data Index: 687513 (C4 (Web Text))

Max Activating Token Index: 206

Text #17

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0236. Min Act: -0.0002

Data Index: 203277 (C4 (Web Text))

Max Activating Token Index: 339

Text #18

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0242. Min Act: -0.0003

Data Index: 1171120 (C4 (Web Text))

Max Activating Token Index: 480

Text #19

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0237. Min Act: -0.0003

Data Index: 1191889 (C4 (Web Text))

Max Activating Token Index: 39