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

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

Neuron 5209 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3245. Min Range: -1.3245

Max Act: 1.3245. Min Act: -0.0000

Data Index: 1146581 (C4 (Web Text))

Max Activating Token Index: 839

Text #1

Max Range: 1.3245. Min Range: -1.3245

Max Act: 1.2231. Min Act: -0.0000

Data Index: 984708 (C4 (Web Text))

Max Activating Token Index: 655

Text #2

Max Range: 1.3245. Min Range: -1.3245

Max Act: 1.1458. Min Act: -0.0000

Data Index: 1129691 (C4 (Web Text))

Max Activating Token Index: 544

Text #3

Max Range: 1.3245. Min Range: -1.3245

Max Act: 1.0488. Min Act: -0.0000

Data Index: 872575 (C4 (Web Text))

Max Activating Token Index: 717

Text #4

Max Range: 1.3245. Min Range: -1.3245

Max Act: 1.0843. Min Act: -0.0000

Data Index: 1177811 (C4 (Web Text))

Max Activating Token Index: 492

Text #5

Max Range: 1.3245. Min Range: -1.3245

Max Act: 1.0293. Min Act: -0.0000

Data Index: 438164 (C4 (Web Text))

Max Activating Token Index: 242

Text #6

Max Range: 1.3245. Min Range: -1.3245

Max Act: 1.0436. Min Act: 0.0000

Data Index: 520011 (C4 (Web Text))

Max Activating Token Index: 969

Text #7

Max Range: 1.3245. Min Range: -1.3245

Max Act: 1.0399. Min Act: -0.0000

Data Index: 286708 (C4 (Web Text))

Max Activating Token Index: 567

Text #8

Max Range: 1.3245. Min Range: -1.3245

Max Act: 1.0180. Min Act: -0.0000

Data Index: 560768 (C4 (Web Text))

Max Activating Token Index: 452

Text #9

Max Range: 1.3245. Min Range: -1.3245

Max Act: 0.9962. Min Act: -0.0000

Data Index: 836855 (C4 (Web Text))

Max Activating Token Index: 908

Text #10

Max Range: 1.3245. Min Range: -1.3245

Max Act: 0.9786. Min Act: -0.0000

Data Index: 1232845 (C4 (Web Text))

Max Activating Token Index: 608

Text #11

Max Range: 1.3245. Min Range: -1.3245

Max Act: 0.9219. Min Act: -0.0000

Data Index: 114749 (C4 (Web Text))

Max Activating Token Index: 655

Text #12

Max Range: 1.3245. Min Range: -1.3245

Max Act: 0.9579. Min Act: -0.0000

Data Index: 430768 (C4 (Web Text))

Max Activating Token Index: 680

Text #13

Max Range: 1.3245. Min Range: -1.3245

Max Act: 0.9622. Min Act: -0.0000

Data Index: 252324 (C4 (Web Text))

Max Activating Token Index: 409

Text #14

Max Range: 1.3245. Min Range: -1.3245

Max Act: 0.8951. Min Act: 0.0000

Data Index: 262694 (C4 (Web Text))

Max Activating Token Index: 839

Text #15

Max Range: 1.3245. Min Range: -1.3245

Max Act: 0.9518. Min Act: -0.0000

Data Index: 48364 (C4 (Web Text))

Max Activating Token Index: 357

Text #16

Max Range: 1.3245. Min Range: -1.3245

Max Act: 0.9495. Min Act: 0.0001

Data Index: 421910 (C4 (Web Text))

Max Activating Token Index: 408

Text #17

Max Range: 1.3245. Min Range: -1.3245

Max Act: 0.9473. Min Act: -0.0000

Data Index: 35436 (C4 (Web Text))

Max Activating Token Index: 689

Text #18

Max Range: 1.3245. Min Range: -1.3245

Max Act: 0.9366. Min Act: -0.0000

Data Index: 1223812 (C4 (Web Text))

Max Activating Token Index: 939

Text #19

Max Range: 1.3245. Min Range: -1.3245

Max Act: 0.9291. Min Act: -0.0000

Data Index: 67590 (C4 (Web Text))

Max Activating Token Index: 96