Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 600 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0321. Min Act: -0.0003

Data Index: 1003922 (C4 (Web Text))

Max Activating Token Index: 796

Text #1

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0315. Min Act: -0.0003

Data Index: 607890 (C4 (Web Text))

Max Activating Token Index: 67

Text #2

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0302. Min Act: -0.0003

Data Index: 945399 (C4 (Web Text))

Max Activating Token Index: 136

Text #3

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0294. Min Act: -0.0002

Data Index: 422668 (C4 (Web Text))

Max Activating Token Index: 657

Text #4

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0292. Min Act: -0.0003

Data Index: 731297 (C4 (Web Text))

Max Activating Token Index: 848

Text #5

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0283. Min Act: -0.0003

Data Index: 1113238 (C4 (Web Text))

Max Activating Token Index: 701

Text #6

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0281. Min Act: -0.0003

Data Index: 1263063 (C4 (Web Text))

Max Activating Token Index: 289

Text #7

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0282. Min Act: -0.0004

Data Index: 1204805 (C4 (Web Text))

Max Activating Token Index: 118

Text #8

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0273. Min Act: -0.0003

Data Index: 315177 (C4 (Web Text))

Max Activating Token Index: 864

Text #9

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0281. Min Act: -0.0003

Data Index: 794005 (C4 (Web Text))

Max Activating Token Index: 935

Text #10

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0271. Min Act: -0.0003

Data Index: 424222 (C4 (Web Text))

Max Activating Token Index: 125

Text #11

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0274. Min Act: -0.0004

Data Index: 203259 (C4 (Web Text))

Max Activating Token Index: 665

Text #12

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0281. Min Act: -0.0003

Data Index: 1198053 (C4 (Web Text))

Max Activating Token Index: 561

Text #13

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0272. Min Act: -0.0003

Data Index: 1310030 (C4 (Web Text))

Max Activating Token Index: 44

Text #14

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0269. Min Act: -0.0003

Data Index: 1022484 (C4 (Web Text))

Max Activating Token Index: 888

Text #15

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0273. Min Act: -0.0003

Data Index: 1026880 (C4 (Web Text))

Max Activating Token Index: 427

Text #16

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0266. Min Act: -0.0003

Data Index: 1289027 (C4 (Web Text))

Max Activating Token Index: 381

Text #17

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0262. Min Act: -0.0003

Data Index: 458220 (C4 (Web Text))

Max Activating Token Index: 592

Text #18

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0264. Min Act: -0.0003

Data Index: 438021 (C4 (Web Text))

Max Activating Token Index: 850

Text #19

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0260. Min Act: -0.0003

Data Index: 17556 (C4 (Web Text))

Max Activating Token Index: 703