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

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

Neuron 195 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: 0.0384. Min Range: -0.0384

Max Act: 0.0384. Min Act: -0.0003

Data Index: 897238 (C4 (Web Text))

Max Activating Token Index: 335

Text #1

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0353. Min Act: -0.0003

Data Index: 178184 (C4 (Web Text))

Max Activating Token Index: 658

Text #2

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0346. Min Act: -0.0003

Data Index: 1093149 (C4 (Web Text))

Max Activating Token Index: 548

Text #3

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0344. Min Act: -0.0003

Data Index: 681824 (C4 (Web Text))

Max Activating Token Index: 641

Text #4

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0333. Min Act: -0.0003

Data Index: 940053 (C4 (Web Text))

Max Activating Token Index: 886

Text #5

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0324. Min Act: -0.0002

Data Index: 1226038 (C4 (Web Text))

Max Activating Token Index: 411

Text #6

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0312. Min Act: -0.0002

Data Index: 416948 (C4 (Web Text))

Max Activating Token Index: 682

Text #7

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0302. Min Act: -0.0003

Data Index: 789971 (C4 (Web Text))

Max Activating Token Index: 89

Text #8

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0292. Min Act: -0.0003

Data Index: 1256427 (C4 (Web Text))

Max Activating Token Index: 648

Text #9

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0299. Min Act: -0.0003

Data Index: 15150 (C4 (Web Text))

Max Activating Token Index: 771

Text #10

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0297. Min Act: -0.0002

Data Index: 349730 (C4 (Web Text))

Max Activating Token Index: 465

Text #11

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0297. Min Act: -0.0003

Data Index: 813483 (C4 (Web Text))

Max Activating Token Index: 730

Text #12

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0288. Min Act: -0.0002

Data Index: 279899 (C4 (Web Text))

Max Activating Token Index: 495

Text #13

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0289. Min Act: -0.0002

Data Index: 816680 (C4 (Web Text))

Max Activating Token Index: 766

Text #14

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0279. Min Act: -0.0003

Data Index: 354202 (C4 (Web Text))

Max Activating Token Index: 771

Text #15

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0302. Min Act: -0.0002

Data Index: 449605 (C4 (Web Text))

Max Activating Token Index: 273

Text #16

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0300. Min Act: -0.0003

Data Index: 680442 (C4 (Web Text))

Max Activating Token Index: 737

Text #17

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0287. Min Act: -0.0003

Data Index: 278032 (C4 (Web Text))

Max Activating Token Index: 134

Text #18

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0286. Min Act: -0.0003

Data Index: 529805 (C4 (Web Text))

Max Activating Token Index: 852

Text #19

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0292. Min Act: -0.0002

Data Index: 611237 (C4 (Web Text))

Max Activating Token Index: 441