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

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

Neuron 3999 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.1119. Min Act: -0.0001

Data Index: 301100 (C4 (Web Text))

Max Activating Token Index: 261

Text #1

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.1145. Min Act: -0.0001

Data Index: 1084412 (C4 (Web Text))

Max Activating Token Index: 467

Text #2

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.1124. Min Act: -0.0001

Data Index: 1217877 (C4 (Web Text))

Max Activating Token Index: 306

Text #3

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.1168. Min Act: -0.0001

Data Index: 962580 (C4 (Web Text))

Max Activating Token Index: 616

Text #4

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.1032. Min Act: -0.0001

Data Index: 917170 (C4 (Web Text))

Max Activating Token Index: 53

Text #5

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.1060. Min Act: -0.0002

Data Index: 1087017 (C4 (Web Text))

Max Activating Token Index: 54

Text #6

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.1020. Min Act: -0.0002

Data Index: 980893 (C4 (Web Text))

Max Activating Token Index: 249

Text #7

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.0974. Min Act: -0.0001

Data Index: 634802 (C4 (Web Text))

Max Activating Token Index: 43

Text #8

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.1036. Min Act: -0.0001

Data Index: 593586 (C4 (Web Text))

Max Activating Token Index: 936

Text #9

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.1035. Min Act: -0.0001

Data Index: 1162309 (C4 (Web Text))

Max Activating Token Index: 900

Text #10

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.0989. Min Act: -0.0001

Data Index: 1327057 (C4 (Web Text))

Max Activating Token Index: 758

Text #11

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.1037. Min Act: -0.0001

Data Index: 1058781 (C4 (Web Text))

Max Activating Token Index: 588

Text #12

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.0950. Min Act: -0.0001

Data Index: 413680 (C4 (Web Text))

Max Activating Token Index: 793

Text #13

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.0946. Min Act: -0.0001

Data Index: 1069626 (C4 (Web Text))

Max Activating Token Index: 812

Text #14

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.0946. Min Act: -0.0001

Data Index: 434660 (C4 (Web Text))

Max Activating Token Index: 920

Text #15

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.0974. Min Act: -0.0001

Data Index: 401018 (C4 (Web Text))

Max Activating Token Index: 351

Text #16

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.0927. Min Act: -0.0002

Data Index: 835223 (C4 (Web Text))

Max Activating Token Index: 796

Text #17

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.0946. Min Act: -0.0001

Data Index: 54530 (C4 (Web Text))

Max Activating Token Index: 608

Text #18

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.0951. Min Act: -0.0001

Data Index: 732675 (C4 (Web Text))

Max Activating Token Index: 688

Text #19

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.0963. Min Act: -0.0001

Data Index: 900765 (C4 (Web Text))

Max Activating Token Index: 915