Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 385 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3061. Min Range: -0.3061

Max Act: 0.3061. Min Act: -0.0002

Data Index: 558257 (C4 (Web Text))

Max Activating Token Index: 10

Text #1

Max Range: 0.3061. Min Range: -0.3061

Max Act: 0.3048. Min Act: -0.0003

Data Index: 1232851 (C4 (Web Text))

Max Activating Token Index: 831

Text #2

Max Range: 0.3061. Min Range: -0.3061

Max Act: 0.2938. Min Act: -0.0002

Data Index: 86548 (C4 (Web Text))

Max Activating Token Index: 526

Text #3

Max Range: 0.3061. Min Range: -0.3061

Max Act: 0.2440. Min Act: -0.0002

Data Index: 55164 (C4 (Web Text))

Max Activating Token Index: 650

Text #4

Max Range: 0.3061. Min Range: -0.3061

Max Act: 0.2320. Min Act: -0.0003

Data Index: 356543 (C4 (Web Text))

Max Activating Token Index: 493

Text #5

Max Range: 0.3061. Min Range: -0.3061

Max Act: 0.2265. Min Act: -0.0002

Data Index: 1051746 (C4 (Web Text))

Max Activating Token Index: 78

Text #6

Max Range: 0.3061. Min Range: -0.3061

Max Act: 0.2244. Min Act: -0.0003

Data Index: 842350 (C4 (Web Text))

Max Activating Token Index: 31

Text #7

Max Range: 0.3061. Min Range: -0.3061

Max Act: 0.2232. Min Act: -0.0003

Data Index: 351927 (C4 (Web Text))

Max Activating Token Index: 793

Text #8

Max Range: 0.3061. Min Range: -0.3061

Max Act: 0.2140. Min Act: -0.0002

Data Index: 984407 (C4 (Web Text))

Max Activating Token Index: 264

Text #9

Max Range: 0.3061. Min Range: -0.3061

Max Act: 0.2045. Min Act: -0.0003

Data Index: 1155443 (C4 (Web Text))

Max Activating Token Index: 237

Text #10

Max Range: 0.3061. Min Range: -0.3061

Max Act: 0.2105. Min Act: -0.0003

Data Index: 667351 (C4 (Web Text))

Max Activating Token Index: 83

Text #11

Max Range: 0.3061. Min Range: -0.3061

Max Act: 0.2007. Min Act: -0.0003

Data Index: 233188 (C4 (Web Text))

Max Activating Token Index: 657

Text #12

Max Range: 0.3061. Min Range: -0.3061

Max Act: 0.1997. Min Act: -0.0003

Data Index: 351267 (C4 (Web Text))

Max Activating Token Index: 828

Text #13

Max Range: 0.3061. Min Range: -0.3061

Max Act: 0.1997. Min Act: -0.0002

Data Index: 681928 (C4 (Web Text))

Max Activating Token Index: 206

Text #14

Max Range: 0.3061. Min Range: -0.3061

Max Act: 0.1989. Min Act: -0.0002

Data Index: 1254346 (C4 (Web Text))

Max Activating Token Index: 829

Text #15

Max Range: 0.3061. Min Range: -0.3061

Max Act: 0.1958. Min Act: -0.0002

Data Index: 754086 (C4 (Web Text))

Max Activating Token Index: 923

Text #16

Max Range: 0.3061. Min Range: -0.3061

Max Act: 0.1954. Min Act: -0.0002

Data Index: 920773 (C4 (Web Text))

Max Activating Token Index: 957

Text #17

Max Range: 0.3061. Min Range: -0.3061

Max Act: 0.1928. Min Act: -0.0003

Data Index: 469703 (C4 (Web Text))

Max Activating Token Index: 716

Text #18

Max Range: 0.3061. Min Range: -0.3061

Max Act: 0.1856. Min Act: -0.0003

Data Index: 703171 (C4 (Web Text))

Max Activating Token Index: 75

Text #19

Max Range: 0.3061. Min Range: -0.3061

Max Act: 0.1925. Min Act: -0.0003

Data Index: 679041 (C4 (Web Text))

Max Activating Token Index: 275