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

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

Neuron 548 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2354. Min Range: -1.2354

Max Act: 1.2354. Min Act: -0.0000

Data Index: 272540 (C4 (Web Text))

Max Activating Token Index: 1014

Text #1

Max Range: 1.2354. Min Range: -1.2354

Max Act: 1.2197. Min Act: -0.0000

Data Index: 151087 (C4 (Web Text))

Max Activating Token Index: 787

Text #2

Max Range: 1.2354. Min Range: -1.2354

Max Act: 1.1352. Min Act: -0.0000

Data Index: 357538 (C4 (Web Text))

Max Activating Token Index: 431

Text #3

Max Range: 1.2354. Min Range: -1.2354

Max Act: 1.0820. Min Act: -0.0000

Data Index: 936257 (C4 (Web Text))

Max Activating Token Index: 1020

Text #4

Max Range: 1.2354. Min Range: -1.2354

Max Act: 1.2212. Min Act: -0.0000

Data Index: 1123536 (C4 (Web Text))

Max Activating Token Index: 755

Text #5

Max Range: 1.2354. Min Range: -1.2354

Max Act: 1.0885. Min Act: -0.0000

Data Index: 574514 (C4 (Web Text))

Max Activating Token Index: 746

Text #6

Max Range: 1.2354. Min Range: -1.2354

Max Act: 1.0581. Min Act: -0.0000

Data Index: 1085174 (C4 (Web Text))

Max Activating Token Index: 52

Text #7

Max Range: 1.2354. Min Range: -1.2354

Max Act: 1.0898. Min Act: -0.0000

Data Index: 591725 (C4 (Web Text))

Max Activating Token Index: 944

Text #8

Max Range: 1.2354. Min Range: -1.2354

Max Act: 1.0516. Min Act: -0.0000

Data Index: 1256373 (C4 (Web Text))

Max Activating Token Index: 233

Text #9

Max Range: 1.2354. Min Range: -1.2354

Max Act: 1.0775. Min Act: -0.0000

Data Index: 1261999 (C4 (Web Text))

Max Activating Token Index: 65

Text #10

Max Range: 1.2354. Min Range: -1.2354

Max Act: 0.9836. Min Act: -0.0000

Data Index: 795116 (C4 (Web Text))

Max Activating Token Index: 44

Text #11

Max Range: 1.2354. Min Range: -1.2354

Max Act: 1.0757. Min Act: -0.0000

Data Index: 464918 (C4 (Web Text))

Max Activating Token Index: 595

Text #12

Max Range: 1.2354. Min Range: -1.2354

Max Act: 1.0159. Min Act: -0.0000

Data Index: 588327 (C4 (Web Text))

Max Activating Token Index: 679

Text #13

Max Range: 1.2354. Min Range: -1.2354

Max Act: 0.9168. Min Act: -0.0000

Data Index: 310708 (C4 (Web Text))

Max Activating Token Index: 928

Text #14

Max Range: 1.2354. Min Range: -1.2354

Max Act: 0.9916. Min Act: -0.0000

Data Index: 1603739 (Python Code)

Max Activating Token Index: 31

Text #15

Max Range: 1.2354. Min Range: -1.2354

Max Act: 1.0415. Min Act: -0.0000

Data Index: 52872 (C4 (Web Text))

Max Activating Token Index: 851

Text #16

Max Range: 1.2354. Min Range: -1.2354

Max Act: 0.9513. Min Act: -0.0000

Data Index: 103375 (C4 (Web Text))

Max Activating Token Index: 107

Text #17

Max Range: 1.2354. Min Range: -1.2354

Max Act: 0.9688. Min Act: -0.0000

Data Index: 152563 (C4 (Web Text))

Max Activating Token Index: 687

Text #18

Max Range: 1.2354. Min Range: -1.2354

Max Act: 0.8629. Min Act: -0.0000

Data Index: 904446 (C4 (Web Text))

Max Activating Token Index: 339

Text #19

Max Range: 1.2354. Min Range: -1.2354

Max Act: 1.0422. Min Act: -0.0000

Data Index: 1033974 (C4 (Web Text))

Max Activating Token Index: 1013