Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3337 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1209. Min Range: -0.1209

Max Act: 0.1209. Min Act: -0.0002

Data Index: 489447 (C4 (Web Text))

Max Activating Token Index: 786

Text #1

Max Range: 0.1209. Min Range: -0.1209

Max Act: 0.1086. Min Act: -0.0002

Data Index: 365628 (C4 (Web Text))

Max Activating Token Index: 189

Text #2

Max Range: 0.1209. Min Range: -0.1209

Max Act: 0.1063. Min Act: -0.0002

Data Index: 638154 (C4 (Web Text))

Max Activating Token Index: 196

Text #3

Max Range: 0.1209. Min Range: -0.1209

Max Act: 0.1075. Min Act: -0.0002

Data Index: 622390 (C4 (Web Text))

Max Activating Token Index: 401

Text #4

Max Range: 0.1209. Min Range: -0.1209

Max Act: 0.1032. Min Act: -0.0002

Data Index: 574552 (C4 (Web Text))

Max Activating Token Index: 137

Text #5

Max Range: 0.1209. Min Range: -0.1209

Max Act: 0.1047. Min Act: -0.0002

Data Index: 915825 (C4 (Web Text))

Max Activating Token Index: 831

Text #6

Max Range: 0.1209. Min Range: -0.1209

Max Act: 0.1048. Min Act: -0.0002

Data Index: 117513 (C4 (Web Text))

Max Activating Token Index: 96

Text #7

Max Range: 0.1209. Min Range: -0.1209

Max Act: 0.0999. Min Act: -0.0002

Data Index: 910878 (C4 (Web Text))

Max Activating Token Index: 83

Text #8

Max Range: 0.1209. Min Range: -0.1209

Max Act: 0.0990. Min Act: -0.0002

Data Index: 733669 (C4 (Web Text))

Max Activating Token Index: 667

Text #9

Max Range: 0.1209. Min Range: -0.1209

Max Act: 0.1027. Min Act: -0.0002

Data Index: 390764 (C4 (Web Text))

Max Activating Token Index: 928

Text #10

Max Range: 0.1209. Min Range: -0.1209

Max Act: 0.0986. Min Act: -0.0002

Data Index: 643135 (C4 (Web Text))

Max Activating Token Index: 196

Text #11

Max Range: 0.1209. Min Range: -0.1209

Max Act: 0.0953. Min Act: -0.0002

Data Index: 715426 (C4 (Web Text))

Max Activating Token Index: 310

Text #12

Max Range: 0.1209. Min Range: -0.1209

Max Act: 0.1019. Min Act: -0.0002

Data Index: 1132528 (C4 (Web Text))

Max Activating Token Index: 285

Text #13

Max Range: 0.1209. Min Range: -0.1209

Max Act: 0.0973. Min Act: -0.0002

Data Index: 345799 (C4 (Web Text))

Max Activating Token Index: 773

Text #14

Max Range: 0.1209. Min Range: -0.1209

Max Act: 0.0975. Min Act: -0.0002

Data Index: 998356 (C4 (Web Text))

Max Activating Token Index: 122

Text #15

Max Range: 0.1209. Min Range: -0.1209

Max Act: 0.1007. Min Act: -0.0002

Data Index: 1357278 (C4 (Web Text))

Max Activating Token Index: 324

Text #16

Max Range: 0.1209. Min Range: -0.1209

Max Act: 0.0969. Min Act: -0.0002

Data Index: 1132902 (C4 (Web Text))

Max Activating Token Index: 703

Text #17

Max Range: 0.1209. Min Range: -0.1209

Max Act: 0.0993. Min Act: -0.0002

Data Index: 73301 (C4 (Web Text))

Max Activating Token Index: 309

Text #18

Max Range: 0.1209. Min Range: -0.1209

Max Act: 0.0952. Min Act: -0.0002

Data Index: 659019 (C4 (Web Text))

Max Activating Token Index: 209

Text #19

Max Range: 0.1209. Min Range: -0.1209

Max Act: 0.0947. Min Act: -0.0002

Data Index: 20801 (C4 (Web Text))

Max Activating Token Index: 195