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

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

Neuron 5640 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4040. Min Range: -0.4040

Max Act: 0.4040. Min Act: -0.0000

Data Index: 1305323 (C4 (Web Text))

Max Activating Token Index: 479

Text #1

Max Range: 0.4040. Min Range: -0.4040

Max Act: 0.3798. Min Act: -0.0000

Data Index: 368386 (C4 (Web Text))

Max Activating Token Index: 815

Text #2

Max Range: 0.4040. Min Range: -0.4040

Max Act: 0.3686. Min Act: -0.0000

Data Index: 1386116 (Python Code)

Max Activating Token Index: 576

Text #3

Max Range: 0.4040. Min Range: -0.4040

Max Act: 0.3209. Min Act: -0.0000

Data Index: 486946 (C4 (Web Text))

Max Activating Token Index: 672

Text #4

Max Range: 0.4040. Min Range: -0.4040

Max Act: 0.3323. Min Act: -0.0000

Data Index: 690597 (C4 (Web Text))

Max Activating Token Index: 691

Text #5

Max Range: 0.4040. Min Range: -0.4040

Max Act: 0.2915. Min Act: -0.0000

Data Index: 751858 (C4 (Web Text))

Max Activating Token Index: 421

Text #6

Max Range: 0.4040. Min Range: -0.4040

Max Act: 0.3120. Min Act: -0.0000

Data Index: 1295842 (C4 (Web Text))

Max Activating Token Index: 336

Text #7

Max Range: 0.4040. Min Range: -0.4040

Max Act: 0.2927. Min Act: -0.0000

Data Index: 247190 (C4 (Web Text))

Max Activating Token Index: 22

Text #8

Max Range: 0.4040. Min Range: -0.4040

Max Act: 0.2903. Min Act: -0.0000

Data Index: 284206 (C4 (Web Text))

Max Activating Token Index: 655

Text #9

Max Range: 0.4040. Min Range: -0.4040

Max Act: 0.2826. Min Act: -0.0000

Data Index: 295279 (C4 (Web Text))

Max Activating Token Index: 816

Text #10

Max Range: 0.4040. Min Range: -0.4040

Max Act: 0.3023. Min Act: -0.0000

Data Index: 682337 (C4 (Web Text))

Max Activating Token Index: 926

Text #11

Max Range: 0.4040. Min Range: -0.4040

Max Act: 0.2738. Min Act: -0.0000

Data Index: 892119 (C4 (Web Text))

Max Activating Token Index: 694

Text #12

Max Range: 0.4040. Min Range: -0.4040

Max Act: 0.2976. Min Act: -0.0000

Data Index: 654301 (C4 (Web Text))

Max Activating Token Index: 956

Text #13

Max Range: 0.4040. Min Range: -0.4040

Max Act: 0.2779. Min Act: -0.0000

Data Index: 266120 (C4 (Web Text))

Max Activating Token Index: 787

Text #14

Max Range: 0.4040. Min Range: -0.4040

Max Act: 0.2823. Min Act: -0.0000

Data Index: 1133777 (C4 (Web Text))

Max Activating Token Index: 488

Text #15

Max Range: 0.4040. Min Range: -0.4040

Max Act: 0.2725. Min Act: -0.0001

Data Index: 656009 (C4 (Web Text))

Max Activating Token Index: 577

Text #16

Max Range: 0.4040. Min Range: -0.4040

Max Act: 0.2833. Min Act: -0.0000

Data Index: 423188 (C4 (Web Text))

Max Activating Token Index: 289

Text #17

Max Range: 0.4040. Min Range: -0.4040

Max Act: 0.2644. Min Act: -0.0000

Data Index: 1007145 (C4 (Web Text))

Max Activating Token Index: 932

Text #18

Max Range: 0.4040. Min Range: -0.4040

Max Act: 0.2745. Min Act: -0.0000

Data Index: 1350338 (C4 (Web Text))

Max Activating Token Index: 174

Text #19

Max Range: 0.4040. Min Range: -0.4040

Max Act: 0.2567. Min Act: -0.0000

Data Index: 1631788 (Python Code)

Max Activating Token Index: 911