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

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

Neuron 2901 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: 0.7596. Min Range: -0.7596

Max Act: 0.7596. Min Act: -0.0000

Data Index: 282441 (C4 (Web Text))

Max Activating Token Index: 124

Text #1

Max Range: 0.7596. Min Range: -0.7596

Max Act: 0.6911. Min Act: -0.0000

Data Index: 432879 (C4 (Web Text))

Max Activating Token Index: 1010

Text #2

Max Range: 0.7596. Min Range: -0.7596

Max Act: 0.6173. Min Act: -0.0000

Data Index: 1248044 (C4 (Web Text))

Max Activating Token Index: 327

Text #3

Max Range: 0.7596. Min Range: -0.7596

Max Act: 0.6255. Min Act: -0.0000

Data Index: 1307008 (C4 (Web Text))

Max Activating Token Index: 518

Text #4

Max Range: 0.7596. Min Range: -0.7596

Max Act: 0.5322. Min Act: -0.0000

Data Index: 1108508 (C4 (Web Text))

Max Activating Token Index: 838

Text #5

Max Range: 0.7596. Min Range: -0.7596

Max Act: 0.5532. Min Act: -0.0000

Data Index: 201208 (C4 (Web Text))

Max Activating Token Index: 460

Text #6

Max Range: 0.7596. Min Range: -0.7596

Max Act: 0.5193. Min Act: 0.0000

Data Index: 472570 (C4 (Web Text))

Max Activating Token Index: 209

Text #7

Max Range: 0.7596. Min Range: -0.7596

Max Act: 0.5391. Min Act: -0.0000

Data Index: 295559 (C4 (Web Text))

Max Activating Token Index: 721

Text #8

Max Range: 0.7596. Min Range: -0.7596

Max Act: 0.5291. Min Act: -0.0000

Data Index: 592935 (C4 (Web Text))

Max Activating Token Index: 917

Text #9

Max Range: 0.7596. Min Range: -0.7596

Max Act: 0.5186. Min Act: -0.0000

Data Index: 779180 (C4 (Web Text))

Max Activating Token Index: 634

Text #10

Max Range: 0.7596. Min Range: -0.7596

Max Act: 0.5086. Min Act: -0.0000

Data Index: 1143547 (C4 (Web Text))

Max Activating Token Index: 505

Text #11

Max Range: 0.7596. Min Range: -0.7596

Max Act: 0.5071. Min Act: -0.0000

Data Index: 563042 (C4 (Web Text))

Max Activating Token Index: 390

Text #12

Max Range: 0.7596. Min Range: -0.7596

Max Act: 0.4875. Min Act: -0.0000

Data Index: 745138 (C4 (Web Text))

Max Activating Token Index: 48

Text #13

Max Range: 0.7596. Min Range: -0.7596

Max Act: 0.5621. Min Act: -0.0000

Data Index: 782907 (C4 (Web Text))

Max Activating Token Index: 810

Text #14

Max Range: 0.7596. Min Range: -0.7596

Max Act: 0.4908. Min Act: -0.0000

Data Index: 850178 (C4 (Web Text))

Max Activating Token Index: 225

Text #15

Max Range: 0.7596. Min Range: -0.7596

Max Act: 0.5169. Min Act: -0.0000

Data Index: 771095 (C4 (Web Text))

Max Activating Token Index: 497

Text #16

Max Range: 0.7596. Min Range: -0.7596

Max Act: 0.5155. Min Act: -0.0000

Data Index: 90576 (C4 (Web Text))

Max Activating Token Index: 627

Text #17

Max Range: 0.7596. Min Range: -0.7596

Max Act: 0.4507. Min Act: -0.0000

Data Index: 965372 (C4 (Web Text))

Max Activating Token Index: 48

Text #18

Max Range: 0.7596. Min Range: -0.7596

Max Act: 0.4463. Min Act: -0.0000

Data Index: 448968 (C4 (Web Text))

Max Activating Token Index: 92

Text #19

Max Range: 0.7596. Min Range: -0.7596

Max Act: 0.4620. Min Act: -0.0000

Data Index: 1111657 (C4 (Web Text))

Max Activating Token Index: 566