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

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

Neuron 1213 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1240. Min Range: -0.1240

Max Act: 0.1194. Min Act: -0.0001

Data Index: 841806 (C4 (Web Text))

Max Activating Token Index: 844

Text #1

Max Range: 0.1240. Min Range: -0.1240

Max Act: 0.1223. Min Act: -0.0001

Data Index: 1195071 (C4 (Web Text))

Max Activating Token Index: 1009

Text #2

Max Range: 0.1240. Min Range: -0.1240

Max Act: 0.1240. Min Act: -0.0001

Data Index: 579377 (C4 (Web Text))

Max Activating Token Index: 487

Text #3

Max Range: 0.1240. Min Range: -0.1240

Max Act: 0.1189. Min Act: -0.0001

Data Index: 316652 (C4 (Web Text))

Max Activating Token Index: 838

Text #4

Max Range: 0.1240. Min Range: -0.1240

Max Act: 0.1089. Min Act: -0.0001

Data Index: 544548 (C4 (Web Text))

Max Activating Token Index: 434

Text #5

Max Range: 0.1240. Min Range: -0.1240

Max Act: 0.1152. Min Act: -0.0001

Data Index: 1197325 (C4 (Web Text))

Max Activating Token Index: 940

Text #6

Max Range: 0.1240. Min Range: -0.1240

Max Act: 0.1045. Min Act: -0.0001

Data Index: 1015353 (C4 (Web Text))

Max Activating Token Index: 203

Text #7

Max Range: 0.1240. Min Range: -0.1240

Max Act: 0.1073. Min Act: -0.0001

Data Index: 895345 (C4 (Web Text))

Max Activating Token Index: 696

Text #8

Max Range: 0.1240. Min Range: -0.1240

Max Act: 0.0908. Min Act: -0.0001

Data Index: 231645 (C4 (Web Text))

Max Activating Token Index: 314

Text #9

Max Range: 0.1240. Min Range: -0.1240

Max Act: 0.1077. Min Act: -0.0001

Data Index: 163933 (C4 (Web Text))

Max Activating Token Index: 359

Text #10

Max Range: 0.1240. Min Range: -0.1240

Max Act: 0.0970. Min Act: -0.0001

Data Index: 999444 (C4 (Web Text))

Max Activating Token Index: 859

Text #11

Max Range: 0.1240. Min Range: -0.1240

Max Act: 0.1005. Min Act: -0.0001

Data Index: 841490 (C4 (Web Text))

Max Activating Token Index: 712

Text #12

Max Range: 0.1240. Min Range: -0.1240

Max Act: 0.0957. Min Act: -0.0001

Data Index: 1533081 (Python Code)

Max Activating Token Index: 48

Text #13

Max Range: 0.1240. Min Range: -0.1240

Max Act: 0.0928. Min Act: -0.0001

Data Index: 141453 (C4 (Web Text))

Max Activating Token Index: 232

Text #14

Max Range: 0.1240. Min Range: -0.1240

Max Act: 0.1023. Min Act: -0.0001

Data Index: 47672 (C4 (Web Text))

Max Activating Token Index: 825

Text #15

Max Range: 0.1240. Min Range: -0.1240

Max Act: 0.1058. Min Act: -0.0001

Data Index: 989845 (C4 (Web Text))

Max Activating Token Index: 735

Text #16

Max Range: 0.1240. Min Range: -0.1240

Max Act: 0.1024. Min Act: -0.0001

Data Index: 276512 (C4 (Web Text))

Max Activating Token Index: 755

Text #17

Max Range: 0.1240. Min Range: -0.1240

Max Act: 0.1009. Min Act: -0.0001

Data Index: 914889 (C4 (Web Text))

Max Activating Token Index: 797

Text #18

Max Range: 0.1240. Min Range: -0.1240

Max Act: 0.1021. Min Act: -0.0001

Data Index: 520178 (C4 (Web Text))

Max Activating Token Index: 1018

Text #19

Max Range: 0.1240. Min Range: -0.1240

Max Act: 0.0867. Min Act: -0.0001

Data Index: 1090056 (C4 (Web Text))

Max Activating Token Index: 441