Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2021 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0467. Min Act: -0.0002

Data Index: 1071860 (C4 (Web Text))

Max Activating Token Index: 167

Text #1

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0436. Min Act: -0.0002

Data Index: 423993 (C4 (Web Text))

Max Activating Token Index: 485

Text #2

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0400. Min Act: -0.0002

Data Index: 1217323 (C4 (Web Text))

Max Activating Token Index: 138

Text #3

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0394. Min Act: -0.0002

Data Index: 683200 (C4 (Web Text))

Max Activating Token Index: 796

Text #4

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0381. Min Act: -0.0002

Data Index: 471674 (C4 (Web Text))

Max Activating Token Index: 99

Text #5

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0372. Min Act: -0.0002

Data Index: 1086997 (C4 (Web Text))

Max Activating Token Index: 160

Text #6

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0377. Min Act: -0.0002

Data Index: 961878 (C4 (Web Text))

Max Activating Token Index: 175

Text #7

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0373. Min Act: -0.0002

Data Index: 65380 (C4 (Web Text))

Max Activating Token Index: 920

Text #8

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0370. Min Act: -0.0002

Data Index: 1258151 (C4 (Web Text))

Max Activating Token Index: 76

Text #9

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0354. Min Act: -0.0002

Data Index: 280930 (C4 (Web Text))

Max Activating Token Index: 235

Text #10

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0344. Min Act: -0.0002

Data Index: 134550 (C4 (Web Text))

Max Activating Token Index: 432

Text #11

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0355. Min Act: -0.0002

Data Index: 869054 (C4 (Web Text))

Max Activating Token Index: 154

Text #12

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0337. Min Act: -0.0002

Data Index: 227763 (C4 (Web Text))

Max Activating Token Index: 195

Text #13

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0341. Min Act: -0.0002

Data Index: 776304 (C4 (Web Text))

Max Activating Token Index: 897

Text #14

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0350. Min Act: -0.0002

Data Index: 1034669 (C4 (Web Text))

Max Activating Token Index: 161

Text #15

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0350. Min Act: -0.0002

Data Index: 1081423 (C4 (Web Text))

Max Activating Token Index: 283

Text #16

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0316. Min Act: -0.0002

Data Index: 91831 (C4 (Web Text))

Max Activating Token Index: 918

Text #17

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0323. Min Act: -0.0002

Data Index: 1067481 (C4 (Web Text))

Max Activating Token Index: 769

Text #18

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0303. Min Act: -0.0002

Data Index: 904069 (C4 (Web Text))

Max Activating Token Index: 469

Text #19

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0301. Min Act: -0.0002

Data Index: 1114696 (C4 (Web Text))

Max Activating Token Index: 138