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

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

Neuron 2090 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1119. Min Range: -0.1119

Max Act: 0.1119. Min Act: -0.0001

Data Index: 462535 (C4 (Web Text))

Max Activating Token Index: 968

Text #1

Max Range: 0.1119. Min Range: -0.1119

Max Act: 0.1103. Min Act: -0.0001

Data Index: 141063 (C4 (Web Text))

Max Activating Token Index: 142

Text #2

Max Range: 0.1119. Min Range: -0.1119

Max Act: 0.1092. Min Act: -0.0001

Data Index: 982303 (C4 (Web Text))

Max Activating Token Index: 295

Text #3

Max Range: 0.1119. Min Range: -0.1119

Max Act: 0.1068. Min Act: -0.0001

Data Index: 1000595 (C4 (Web Text))

Max Activating Token Index: 666

Text #4

Max Range: 0.1119. Min Range: -0.1119

Max Act: 0.1075. Min Act: -0.0001

Data Index: 956882 (C4 (Web Text))

Max Activating Token Index: 120

Text #5

Max Range: 0.1119. Min Range: -0.1119

Max Act: 0.1080. Min Act: -0.0001

Data Index: 43302 (C4 (Web Text))

Max Activating Token Index: 721

Text #6

Max Range: 0.1119. Min Range: -0.1119

Max Act: 0.1018. Min Act: -0.0001

Data Index: 388103 (C4 (Web Text))

Max Activating Token Index: 1009

Text #7

Max Range: 0.1119. Min Range: -0.1119

Max Act: 0.1030. Min Act: -0.0001

Data Index: 1219727 (C4 (Web Text))

Max Activating Token Index: 207

Text #8

Max Range: 0.1119. Min Range: -0.1119

Max Act: 0.1017. Min Act: -0.0001

Data Index: 357583 (C4 (Web Text))

Max Activating Token Index: 142

Text #9

Max Range: 0.1119. Min Range: -0.1119

Max Act: 0.0991. Min Act: -0.0001

Data Index: 1192595 (C4 (Web Text))

Max Activating Token Index: 195

Text #10

Max Range: 0.1119. Min Range: -0.1119

Max Act: 0.1028. Min Act: -0.0001

Data Index: 1196559 (C4 (Web Text))

Max Activating Token Index: 216

Text #11

Max Range: 0.1119. Min Range: -0.1119

Max Act: 0.1052. Min Act: -0.0001

Data Index: 1132425 (C4 (Web Text))

Max Activating Token Index: 995

Text #12

Max Range: 0.1119. Min Range: -0.1119

Max Act: 0.1018. Min Act: -0.0001

Data Index: 283759 (C4 (Web Text))

Max Activating Token Index: 292

Text #13

Max Range: 0.1119. Min Range: -0.1119

Max Act: 0.0972. Min Act: -0.0001

Data Index: 1102581 (C4 (Web Text))

Max Activating Token Index: 241

Text #14

Max Range: 0.1119. Min Range: -0.1119

Max Act: 0.1006. Min Act: -0.0001

Data Index: 1012266 (C4 (Web Text))

Max Activating Token Index: 460

Text #15

Max Range: 0.1119. Min Range: -0.1119

Max Act: 0.1043. Min Act: -0.0001

Data Index: 208197 (C4 (Web Text))

Max Activating Token Index: 959

Text #16

Max Range: 0.1119. Min Range: -0.1119

Max Act: 0.1003. Min Act: -0.0001

Data Index: 1497764 (Python Code)

Max Activating Token Index: 734

Text #17

Max Range: 0.1119. Min Range: -0.1119

Max Act: 0.1012. Min Act: -0.0001

Data Index: 329214 (C4 (Web Text))

Max Activating Token Index: 976

Text #18

Max Range: 0.1119. Min Range: -0.1119

Max Act: 0.0920. Min Act: -0.0001

Data Index: 356009 (C4 (Web Text))

Max Activating Token Index: 867

Text #19

Max Range: 0.1119. Min Range: -0.1119

Max Act: 0.0987. Min Act: -0.0001

Data Index: 421861 (C4 (Web Text))

Max Activating Token Index: 354