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

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

Neuron 2827 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: 1.5922. Min Range: -1.5922

Max Act: 1.5922. Min Act: -0.0002

Data Index: 130470 (C4 (Web Text))

Max Activating Token Index: 286

Text #1

Max Range: 1.5922. Min Range: -1.5922

Max Act: 1.5175. Min Act: -0.0002

Data Index: 627399 (C4 (Web Text))

Max Activating Token Index: 158

Text #2

Max Range: 1.5922. Min Range: -1.5922

Max Act: 1.3957. Min Act: -0.0002

Data Index: 459239 (C4 (Web Text))

Max Activating Token Index: 439

Text #3

Max Range: 1.5922. Min Range: -1.5922

Max Act: 1.2755. Min Act: -0.0002

Data Index: 266112 (C4 (Web Text))

Max Activating Token Index: 338

Text #4

Max Range: 1.5922. Min Range: -1.5922

Max Act: 1.1374. Min Act: -0.0002

Data Index: 103501 (C4 (Web Text))

Max Activating Token Index: 691

Text #5

Max Range: 1.5922. Min Range: -1.5922

Max Act: 1.1886. Min Act: -0.0002

Data Index: 795410 (C4 (Web Text))

Max Activating Token Index: 755

Text #6

Max Range: 1.5922. Min Range: -1.5922

Max Act: 1.1477. Min Act: -0.0002

Data Index: 1275695 (C4 (Web Text))

Max Activating Token Index: 424

Text #7

Max Range: 1.5922. Min Range: -1.5922

Max Act: 1.2280. Min Act: -0.0002

Data Index: 273571 (C4 (Web Text))

Max Activating Token Index: 734

Text #8

Max Range: 1.5922. Min Range: -1.5922

Max Act: 1.0812. Min Act: -0.0002

Data Index: 434101 (C4 (Web Text))

Max Activating Token Index: 55

Text #9

Max Range: 1.5922. Min Range: -1.5922

Max Act: 1.1956. Min Act: -0.0002

Data Index: 118342 (C4 (Web Text))

Max Activating Token Index: 715

Text #10

Max Range: 1.5922. Min Range: -1.5922

Max Act: 1.1226. Min Act: -0.0002

Data Index: 525441 (C4 (Web Text))

Max Activating Token Index: 653

Text #11

Max Range: 1.5922. Min Range: -1.5922

Max Act: 1.0872. Min Act: -0.0002

Data Index: 499676 (C4 (Web Text))

Max Activating Token Index: 33

Text #12

Max Range: 1.5922. Min Range: -1.5922

Max Act: 1.1278. Min Act: -0.0002

Data Index: 149364 (C4 (Web Text))

Max Activating Token Index: 337

Text #13

Max Range: 1.5922. Min Range: -1.5922

Max Act: 1.0642. Min Act: -0.0002

Data Index: 696074 (C4 (Web Text))

Max Activating Token Index: 287

Text #14

Max Range: 1.5922. Min Range: -1.5922

Max Act: 1.0888. Min Act: -0.0002

Data Index: 910989 (C4 (Web Text))

Max Activating Token Index: 431

Text #15

Max Range: 1.5922. Min Range: -1.5922

Max Act: 1.0116. Min Act: -0.0002

Data Index: 224872 (C4 (Web Text))

Max Activating Token Index: 444

Text #16

Max Range: 1.5922. Min Range: -1.5922

Max Act: 1.0363. Min Act: -0.0002

Data Index: 963842 (C4 (Web Text))

Max Activating Token Index: 153

Text #17

Max Range: 1.5922. Min Range: -1.5922

Max Act: 1.0195. Min Act: -0.0002

Data Index: 206916 (C4 (Web Text))

Max Activating Token Index: 596

Text #18

Max Range: 1.5922. Min Range: -1.5922

Max Act: 1.0360. Min Act: -0.0002

Data Index: 16388 (C4 (Web Text))

Max Activating Token Index: 1006

Text #19

Max Range: 1.5922. Min Range: -1.5922

Max Act: 1.0960. Min Act: -0.0002

Data Index: 1216587 (C4 (Web Text))

Max Activating Token Index: 889