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

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

Neuron 3683 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.1311. Min Act: -0.0002

Data Index: 195276 (C4 (Web Text))

Max Activating Token Index: 646

Text #1

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.1256. Min Act: -0.0002

Data Index: 573985 (C4 (Web Text))

Max Activating Token Index: 667

Text #2

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.1253. Min Act: -0.0002

Data Index: 999550 (C4 (Web Text))

Max Activating Token Index: 408

Text #3

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.1245. Min Act: -0.0002

Data Index: 987275 (C4 (Web Text))

Max Activating Token Index: 954

Text #4

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.1185. Min Act: -0.0002

Data Index: 423390 (C4 (Web Text))

Max Activating Token Index: 906

Text #5

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.1158. Min Act: -0.0002

Data Index: 251477 (C4 (Web Text))

Max Activating Token Index: 221

Text #6

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.1149. Min Act: -0.0002

Data Index: 434869 (C4 (Web Text))

Max Activating Token Index: 990

Text #7

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.1136. Min Act: -0.0002

Data Index: 237568 (C4 (Web Text))

Max Activating Token Index: 560

Text #8

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.1053. Min Act: -0.0001

Data Index: 1076211 (C4 (Web Text))

Max Activating Token Index: 174

Text #9

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.1048. Min Act: -0.0002

Data Index: 1321049 (C4 (Web Text))

Max Activating Token Index: 563

Text #10

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.1060. Min Act: -0.0002

Data Index: 170777 (C4 (Web Text))

Max Activating Token Index: 692

Text #11

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.1037. Min Act: -0.0002

Data Index: 971621 (C4 (Web Text))

Max Activating Token Index: 893

Text #12

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.1012. Min Act: -0.0002

Data Index: 467600 (C4 (Web Text))

Max Activating Token Index: 305

Text #13

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.1009. Min Act: -0.0001

Data Index: 460962 (C4 (Web Text))

Max Activating Token Index: 914

Text #14

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.1005. Min Act: -0.0002

Data Index: 186177 (C4 (Web Text))

Max Activating Token Index: 502

Text #15

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.0991. Min Act: -0.0002

Data Index: 355321 (C4 (Web Text))

Max Activating Token Index: 607

Text #16

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.0988. Min Act: -0.0002

Data Index: 812811 (C4 (Web Text))

Max Activating Token Index: 741

Text #17

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.0979. Min Act: -0.0002

Data Index: 329557 (C4 (Web Text))

Max Activating Token Index: 147

Text #18

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.0919. Min Act: -0.0002

Data Index: 248212 (C4 (Web Text))

Max Activating Token Index: 136

Text #19

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.0944. Min Act: -0.0001

Data Index: 1172170 (C4 (Web Text))

Max Activating Token Index: 725