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

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

Neuron 1019 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: 0.1258. Min Range: -0.1258

Max Act: 0.1258. Min Act: -0.0001

Data Index: 851372 (C4 (Web Text))

Max Activating Token Index: 520

Text #1

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1152. Min Act: -0.0001

Data Index: 1155314 (C4 (Web Text))

Max Activating Token Index: 294

Text #2

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1139. Min Act: -0.0001

Data Index: 1263180 (C4 (Web Text))

Max Activating Token Index: 275

Text #3

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1095. Min Act: -0.0001

Data Index: 41265 (C4 (Web Text))

Max Activating Token Index: 578

Text #4

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1101. Min Act: -0.0001

Data Index: 858032 (C4 (Web Text))

Max Activating Token Index: 921

Text #5

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1083. Min Act: -0.0001

Data Index: 1004942 (C4 (Web Text))

Max Activating Token Index: 803

Text #6

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1131. Min Act: -0.0001

Data Index: 635041 (C4 (Web Text))

Max Activating Token Index: 888

Text #7

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1122. Min Act: -0.0001

Data Index: 1326725 (C4 (Web Text))

Max Activating Token Index: 951

Text #8

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1021. Min Act: -0.0001

Data Index: 446362 (C4 (Web Text))

Max Activating Token Index: 908

Text #9

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1095. Min Act: -0.0001

Data Index: 861796 (C4 (Web Text))

Max Activating Token Index: 142

Text #10

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1088. Min Act: -0.0001

Data Index: 958121 (C4 (Web Text))

Max Activating Token Index: 446

Text #11

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1058. Min Act: -0.0001

Data Index: 811464 (C4 (Web Text))

Max Activating Token Index: 843

Text #12

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1049. Min Act: -0.0001

Data Index: 1629316 (Python Code)

Max Activating Token Index: 468

Text #13

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1030. Min Act: -0.0001

Data Index: 1574367 (Python Code)

Max Activating Token Index: 589

Text #14

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1037. Min Act: -0.0001

Data Index: 172196 (C4 (Web Text))

Max Activating Token Index: 962

Text #15

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1047. Min Act: -0.0001

Data Index: 1145495 (C4 (Web Text))

Max Activating Token Index: 113

Text #16

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1056. Min Act: -0.0001

Data Index: 612792 (C4 (Web Text))

Max Activating Token Index: 211

Text #17

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1034. Min Act: -0.0001

Data Index: 231524 (C4 (Web Text))

Max Activating Token Index: 340

Text #18

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1007. Min Act: -0.0001

Data Index: 610027 (C4 (Web Text))

Max Activating Token Index: 165

Text #19

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.0961. Min Act: -0.0001

Data Index: 1041318 (C4 (Web Text))

Max Activating Token Index: 927