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

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

Neuron 5068 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0636. Min Act: -0.0002

Data Index: 648919 (C4 (Web Text))

Max Activating Token Index: 164

Text #1

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0642. Min Act: -0.0002

Data Index: 850193 (C4 (Web Text))

Max Activating Token Index: 357

Text #2

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0557. Min Act: -0.0002

Data Index: 405127 (C4 (Web Text))

Max Activating Token Index: 247

Text #3

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0504. Min Act: -0.0002

Data Index: 1038113 (C4 (Web Text))

Max Activating Token Index: 95

Text #4

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0480. Min Act: -0.0002

Data Index: 1048960 (C4 (Web Text))

Max Activating Token Index: 478

Text #5

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0466. Min Act: -0.0002

Data Index: 385555 (C4 (Web Text))

Max Activating Token Index: 553

Text #6

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0457. Min Act: -0.0002

Data Index: 1272518 (C4 (Web Text))

Max Activating Token Index: 1006

Text #7

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0410. Min Act: -0.0002

Data Index: 377583 (C4 (Web Text))

Max Activating Token Index: 565

Text #8

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0434. Min Act: -0.0002

Data Index: 1253604 (C4 (Web Text))

Max Activating Token Index: 657

Text #9

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0457. Min Act: -0.0002

Data Index: 645250 (C4 (Web Text))

Max Activating Token Index: 440

Text #10

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0453. Min Act: -0.0002

Data Index: 119879 (C4 (Web Text))

Max Activating Token Index: 162

Text #11

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0405. Min Act: -0.0002

Data Index: 321268 (C4 (Web Text))

Max Activating Token Index: 401

Text #12

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0406. Min Act: -0.0002

Data Index: 142289 (C4 (Web Text))

Max Activating Token Index: 788

Text #13

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0386. Min Act: -0.0002

Data Index: 1022364 (C4 (Web Text))

Max Activating Token Index: 349

Text #14

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0377. Min Act: -0.0002

Data Index: 917666 (C4 (Web Text))

Max Activating Token Index: 355

Text #15

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0385. Min Act: -0.0002

Data Index: 805674 (C4 (Web Text))

Max Activating Token Index: 684

Text #16

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0375. Min Act: -0.0002

Data Index: 822383 (C4 (Web Text))

Max Activating Token Index: 412

Text #17

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0398. Min Act: -0.0002

Data Index: 599576 (C4 (Web Text))

Max Activating Token Index: 569

Text #18

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0384. Min Act: -0.0002

Data Index: 930550 (C4 (Web Text))

Max Activating Token Index: 440

Text #19

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0396. Min Act: -0.0002

Data Index: 208152 (C4 (Web Text))

Max Activating Token Index: 235