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

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

Neuron 1933 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.2540. Min Act: -0.0000

Data Index: 21539 (C4 (Web Text))

Max Activating Token Index: 154

Text #1

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.2313. Min Act: -0.0000

Data Index: 892391 (C4 (Web Text))

Max Activating Token Index: 1009

Text #2

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.2420. Min Act: -0.0000

Data Index: 1033350 (C4 (Web Text))

Max Activating Token Index: 950

Text #3

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.2335. Min Act: 0.0000

Data Index: 350520 (C4 (Web Text))

Max Activating Token Index: 74

Text #4

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.2244. Min Act: -0.0000

Data Index: 527179 (C4 (Web Text))

Max Activating Token Index: 753

Text #5

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.2219. Min Act: -0.0000

Data Index: 351406 (C4 (Web Text))

Max Activating Token Index: 62

Text #6

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.2125. Min Act: -0.0000

Data Index: 1359235 (C4 (Web Text))

Max Activating Token Index: 912

Text #7

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.2070. Min Act: -0.0000

Data Index: 19727 (C4 (Web Text))

Max Activating Token Index: 457

Text #8

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.2197. Min Act: -0.0000

Data Index: 1068005 (C4 (Web Text))

Max Activating Token Index: 380

Text #9

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.2125. Min Act: -0.0000

Data Index: 1146196 (C4 (Web Text))

Max Activating Token Index: 408

Text #10

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.2112. Min Act: -0.0000

Data Index: 607777 (C4 (Web Text))

Max Activating Token Index: 968

Text #11

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.2072. Min Act: -0.0000

Data Index: 354134 (C4 (Web Text))

Max Activating Token Index: 760

Text #12

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.2156. Min Act: -0.0000

Data Index: 637359 (C4 (Web Text))

Max Activating Token Index: 904

Text #13

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.2014. Min Act: -0.0000

Data Index: 980523 (C4 (Web Text))

Max Activating Token Index: 973

Text #14

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.1885. Min Act: -0.0000

Data Index: 849581 (C4 (Web Text))

Max Activating Token Index: 160

Text #15

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.1770. Min Act: -0.0000

Data Index: 156549 (C4 (Web Text))

Max Activating Token Index: 813

Text #16

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.1928. Min Act: -0.0000

Data Index: 1192206 (C4 (Web Text))

Max Activating Token Index: 62

Text #17

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.1905. Min Act: -0.0000

Data Index: 1205167 (C4 (Web Text))

Max Activating Token Index: 803

Text #18

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.1968. Min Act: -0.0000

Data Index: 969362 (C4 (Web Text))

Max Activating Token Index: 235

Text #19

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.1880. Min Act: -0.0000

Data Index: 1033401 (C4 (Web Text))

Max Activating Token Index: 145