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

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

Neuron 3633 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: 0.3757. Min Range: -0.3757

Max Act: 0.3757. Min Act: -0.0002

Data Index: 898493 (C4 (Web Text))

Max Activating Token Index: 666

Text #1

Max Range: 0.3757. Min Range: -0.3757

Max Act: 0.2682. Min Act: -0.0002

Data Index: 386194 (C4 (Web Text))

Max Activating Token Index: 748

Text #2

Max Range: 0.3757. Min Range: -0.3757

Max Act: 0.2688. Min Act: -0.0002

Data Index: 1255011 (C4 (Web Text))

Max Activating Token Index: 729

Text #3

Max Range: 0.3757. Min Range: -0.3757

Max Act: 0.2682. Min Act: -0.0002

Data Index: 889631 (C4 (Web Text))

Max Activating Token Index: 430

Text #4

Max Range: 0.3757. Min Range: -0.3757

Max Act: 0.2595. Min Act: -0.0002

Data Index: 795143 (C4 (Web Text))

Max Activating Token Index: 754

Text #5

Max Range: 0.3757. Min Range: -0.3757

Max Act: 0.2657. Min Act: -0.0002

Data Index: 721706 (C4 (Web Text))

Max Activating Token Index: 656

Text #6

Max Range: 0.3757. Min Range: -0.3757

Max Act: 0.2588. Min Act: -0.0002

Data Index: 1305673 (C4 (Web Text))

Max Activating Token Index: 294

Text #7

Max Range: 0.3757. Min Range: -0.3757

Max Act: 0.2938. Min Act: -0.0002

Data Index: 666332 (C4 (Web Text))

Max Activating Token Index: 883

Text #8

Max Range: 0.3757. Min Range: -0.3757

Max Act: 0.2587. Min Act: -0.0002

Data Index: 579827 (C4 (Web Text))

Max Activating Token Index: 360

Text #9

Max Range: 0.3757. Min Range: -0.3757

Max Act: 0.2632. Min Act: -0.0002

Data Index: 258637 (C4 (Web Text))

Max Activating Token Index: 447

Text #10

Max Range: 0.3757. Min Range: -0.3757

Max Act: 0.2397. Min Act: -0.0002

Data Index: 1158907 (C4 (Web Text))

Max Activating Token Index: 967

Text #11

Max Range: 0.3757. Min Range: -0.3757

Max Act: 0.2384. Min Act: -0.0002

Data Index: 230066 (C4 (Web Text))

Max Activating Token Index: 105

Text #12

Max Range: 0.3757. Min Range: -0.3757

Max Act: 0.2596. Min Act: -0.0002

Data Index: 380919 (C4 (Web Text))

Max Activating Token Index: 17

Text #13

Max Range: 0.3757. Min Range: -0.3757

Max Act: 0.2464. Min Act: -0.0002

Data Index: 836571 (C4 (Web Text))

Max Activating Token Index: 158

Text #14

Max Range: 0.3757. Min Range: -0.3757

Max Act: 0.2565. Min Act: -0.0002

Data Index: 564779 (C4 (Web Text))

Max Activating Token Index: 3

Text #15

Max Range: 0.3757. Min Range: -0.3757

Max Act: 0.2345. Min Act: -0.0002

Data Index: 242719 (C4 (Web Text))

Max Activating Token Index: 52

Text #16

Max Range: 0.3757. Min Range: -0.3757

Max Act: 0.2352. Min Act: -0.0002

Data Index: 779997 (C4 (Web Text))

Max Activating Token Index: 339

Text #17

Max Range: 0.3757. Min Range: -0.3757

Max Act: 0.2353. Min Act: -0.0002

Data Index: 94980 (C4 (Web Text))

Max Activating Token Index: 369

Text #18

Max Range: 0.3757. Min Range: -0.3757

Max Act: 0.2381. Min Act: -0.0002

Data Index: 393094 (C4 (Web Text))

Max Activating Token Index: 6

Text #19

Max Range: 0.3757. Min Range: -0.3757

Max Act: 0.2436. Min Act: -0.0002

Data Index: 145903 (C4 (Web Text))

Max Activating Token Index: 11