Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1901 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.1389. Min Act: -0.0006

Data Index: 1045433 (C4 (Web Text))

Max Activating Token Index: 859

Text #1

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.1190. Min Act: -0.0006

Data Index: 907528 (C4 (Web Text))

Max Activating Token Index: 694

Text #2

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.1209. Min Act: -0.0006

Data Index: 978886 (C4 (Web Text))

Max Activating Token Index: 879

Text #3

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.1238. Min Act: -0.0006

Data Index: 999068 (C4 (Web Text))

Max Activating Token Index: 945

Text #4

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.1191. Min Act: -0.0006

Data Index: 1157460 (C4 (Web Text))

Max Activating Token Index: 995

Text #5

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.1140. Min Act: -0.0006

Data Index: 845968 (C4 (Web Text))

Max Activating Token Index: 777

Text #6

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.1139. Min Act: -0.0006

Data Index: 446509 (C4 (Web Text))

Max Activating Token Index: 239

Text #7

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.1145. Min Act: -0.0006

Data Index: 88517 (C4 (Web Text))

Max Activating Token Index: 966

Text #8

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.1053. Min Act: -0.0006

Data Index: 962408 (C4 (Web Text))

Max Activating Token Index: 332

Text #9

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.1090. Min Act: -0.0006

Data Index: 577634 (C4 (Web Text))

Max Activating Token Index: 737

Text #10

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.1045. Min Act: -0.0006

Data Index: 1066191 (C4 (Web Text))

Max Activating Token Index: 876

Text #11

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.1083. Min Act: -0.0006

Data Index: 741795 (C4 (Web Text))

Max Activating Token Index: 728

Text #12

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.1075. Min Act: -0.0006

Data Index: 1158039 (C4 (Web Text))

Max Activating Token Index: 167

Text #13

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.1023. Min Act: -0.0006

Data Index: 1103720 (C4 (Web Text))

Max Activating Token Index: 949

Text #14

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.1063. Min Act: -0.0006

Data Index: 1204792 (C4 (Web Text))

Max Activating Token Index: 195

Text #15

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.1058. Min Act: -0.0006

Data Index: 1262856 (C4 (Web Text))

Max Activating Token Index: 936

Text #16

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.1009. Min Act: -0.0006

Data Index: 193896 (C4 (Web Text))

Max Activating Token Index: 882

Text #17

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.0959. Min Act: -0.0006

Data Index: 78891 (C4 (Web Text))

Max Activating Token Index: 110

Text #18

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.1032. Min Act: -0.0006

Data Index: 31934 (C4 (Web Text))

Max Activating Token Index: 399

Text #19

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.1111. Min Act: -0.0006

Data Index: 285426 (C4 (Web Text))

Max Activating Token Index: 469