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

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

Neuron 5743 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: 1.9923. Min Range: -1.9923

Max Act: 1.9780. Min Act: -0.0000

Data Index: 1132777 (C4 (Web Text))

Max Activating Token Index: 155

Text #1

Max Range: 1.9923. Min Range: -1.9923

Max Act: 1.9923. Min Act: 0.0000

Data Index: 1109657 (C4 (Web Text))

Max Activating Token Index: 19

Text #2

Max Range: 1.9923. Min Range: -1.9923

Max Act: 1.8250. Min Act: -0.0000

Data Index: 1091638 (C4 (Web Text))

Max Activating Token Index: 757

Text #3

Max Range: 1.9923. Min Range: -1.9923

Max Act: 1.7315. Min Act: -0.0000

Data Index: 121012 (C4 (Web Text))

Max Activating Token Index: 831

Text #4

Max Range: 1.9923. Min Range: -1.9923

Max Act: 1.5371. Min Act: -0.0000

Data Index: 395051 (C4 (Web Text))

Max Activating Token Index: 93

Text #5

Max Range: 1.9923. Min Range: -1.9923

Max Act: 1.5078. Min Act: -0.0000

Data Index: 961430 (C4 (Web Text))

Max Activating Token Index: 909

Text #6

Max Range: 1.9923. Min Range: -1.9923

Max Act: 1.3733. Min Act: -0.0000

Data Index: 724845 (C4 (Web Text))

Max Activating Token Index: 437

Text #7

Max Range: 1.9923. Min Range: -1.9923

Max Act: 1.4580. Min Act: -0.0000

Data Index: 605416 (C4 (Web Text))

Max Activating Token Index: 248

Text #8

Max Range: 1.9923. Min Range: -1.9923

Max Act: 1.3771. Min Act: -0.0000

Data Index: 186076 (C4 (Web Text))

Max Activating Token Index: 541

Text #9

Max Range: 1.9923. Min Range: -1.9923

Max Act: 1.4271. Min Act: -0.0000

Data Index: 84809 (C4 (Web Text))

Max Activating Token Index: 226

Text #10

Max Range: 1.9923. Min Range: -1.9923

Max Act: 1.4336. Min Act: -0.0000

Data Index: 44071 (C4 (Web Text))

Max Activating Token Index: 48

Text #11

Max Range: 1.9923. Min Range: -1.9923

Max Act: 1.4415. Min Act: -0.0000

Data Index: 638612 (C4 (Web Text))

Max Activating Token Index: 86

Text #12

Max Range: 1.9923. Min Range: -1.9923

Max Act: 1.4289. Min Act: -0.0000

Data Index: 14567 (C4 (Web Text))

Max Activating Token Index: 401

Text #13

Max Range: 1.9923. Min Range: -1.9923

Max Act: 1.4308. Min Act: -0.0000

Data Index: 396567 (C4 (Web Text))

Max Activating Token Index: 597

Text #14

Max Range: 1.9923. Min Range: -1.9923

Max Act: 1.4979. Min Act: -0.0000

Data Index: 306399 (C4 (Web Text))

Max Activating Token Index: 831

Text #15

Max Range: 1.9923. Min Range: -1.9923

Max Act: 1.4811. Min Act: -0.0000

Data Index: 1112394 (C4 (Web Text))

Max Activating Token Index: 335

Text #16

Max Range: 1.9923. Min Range: -1.9923

Max Act: 1.3891. Min Act: -0.0000

Data Index: 1353841 (C4 (Web Text))

Max Activating Token Index: 541

Text #17

Max Range: 1.9923. Min Range: -1.9923

Max Act: 1.3879. Min Act: -0.0000

Data Index: 38237 (C4 (Web Text))

Max Activating Token Index: 34

Text #18

Max Range: 1.9923. Min Range: -1.9923

Max Act: 1.3623. Min Act: 0.0000

Data Index: 228660 (C4 (Web Text))

Max Activating Token Index: 76

Text #19

Max Range: 1.9923. Min Range: -1.9923

Max Act: 1.3488. Min Act: -0.0000

Data Index: 536358 (C4 (Web Text))

Max Activating Token Index: 910