Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2229 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2373. Min Range: -0.2373

Max Act: 0.2373. Min Act: -0.0001

Data Index: 1152871 (C4 (Web Text))

Max Activating Token Index: 937

Text #1

Max Range: 0.2373. Min Range: -0.2373

Max Act: 0.2215. Min Act: -0.0001

Data Index: 753753 (C4 (Web Text))

Max Activating Token Index: 738

Text #2

Max Range: 0.2373. Min Range: -0.2373

Max Act: 0.2221. Min Act: -0.0001

Data Index: 617042 (C4 (Web Text))

Max Activating Token Index: 45

Text #3

Max Range: 0.2373. Min Range: -0.2373

Max Act: 0.2177. Min Act: -0.0001

Data Index: 415925 (C4 (Web Text))

Max Activating Token Index: 632

Text #4

Max Range: 0.2373. Min Range: -0.2373

Max Act: 0.2147. Min Act: -0.0001

Data Index: 992383 (C4 (Web Text))

Max Activating Token Index: 903

Text #5

Max Range: 0.2373. Min Range: -0.2373

Max Act: 0.2088. Min Act: -0.0001

Data Index: 182021 (C4 (Web Text))

Max Activating Token Index: 961

Text #6

Max Range: 0.2373. Min Range: -0.2373

Max Act: 0.2324. Min Act: -0.0001

Data Index: 1332357 (C4 (Web Text))

Max Activating Token Index: 649

Text #7

Max Range: 0.2373. Min Range: -0.2373

Max Act: 0.2002. Min Act: -0.0001

Data Index: 151198 (C4 (Web Text))

Max Activating Token Index: 812

Text #8

Max Range: 0.2373. Min Range: -0.2373

Max Act: 0.2132. Min Act: -0.0001

Data Index: 579849 (C4 (Web Text))

Max Activating Token Index: 706

Text #9

Max Range: 0.2373. Min Range: -0.2373

Max Act: 0.2057. Min Act: -0.0001

Data Index: 349258 (C4 (Web Text))

Max Activating Token Index: 750

Text #10

Max Range: 0.2373. Min Range: -0.2373

Max Act: 0.2181. Min Act: -0.0001

Data Index: 1011261 (C4 (Web Text))

Max Activating Token Index: 431

Text #11

Max Range: 0.2373. Min Range: -0.2373

Max Act: 0.2173. Min Act: -0.0001

Data Index: 133125 (C4 (Web Text))

Max Activating Token Index: 795

Text #12

Max Range: 0.2373. Min Range: -0.2373

Max Act: 0.2121. Min Act: -0.0001

Data Index: 614324 (C4 (Web Text))

Max Activating Token Index: 730

Text #13

Max Range: 0.2373. Min Range: -0.2373

Max Act: 0.2106. Min Act: -0.0001

Data Index: 263346 (C4 (Web Text))

Max Activating Token Index: 850

Text #14

Max Range: 0.2373. Min Range: -0.2373

Max Act: 0.1955. Min Act: -0.0001

Data Index: 1038017 (C4 (Web Text))

Max Activating Token Index: 380

Text #15

Max Range: 0.2373. Min Range: -0.2373

Max Act: 0.1899. Min Act: -0.0001

Data Index: 981525 (C4 (Web Text))

Max Activating Token Index: 806

Text #16

Max Range: 0.2373. Min Range: -0.2373

Max Act: 0.1980. Min Act: -0.0001

Data Index: 236819 (C4 (Web Text))

Max Activating Token Index: 900

Text #17

Max Range: 0.2373. Min Range: -0.2373

Max Act: 0.1974. Min Act: -0.0001

Data Index: 828173 (C4 (Web Text))

Max Activating Token Index: 518

Text #18

Max Range: 0.2373. Min Range: -0.2373

Max Act: 0.2028. Min Act: -0.0001

Data Index: 71416 (C4 (Web Text))

Max Activating Token Index: 982

Text #19

Max Range: 0.2373. Min Range: -0.2373

Max Act: 0.1942. Min Act: -0.0001

Data Index: 1078360 (C4 (Web Text))

Max Activating Token Index: 1017