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

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

Neuron 204 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1258. Min Act: -0.0002

Data Index: 1133323 (C4 (Web Text))

Max Activating Token Index: 275

Text #1

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1201. Min Act: -0.0003

Data Index: 674195 (C4 (Web Text))

Max Activating Token Index: 769

Text #2

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1175. Min Act: -0.0003

Data Index: 1344644 (C4 (Web Text))

Max Activating Token Index: 657

Text #3

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1222. Min Act: -0.0002

Data Index: 1172780 (C4 (Web Text))

Max Activating Token Index: 671

Text #4

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1138. Min Act: -0.0002

Data Index: 846924 (C4 (Web Text))

Max Activating Token Index: 34

Text #5

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1132. Min Act: -0.0002

Data Index: 1346801 (C4 (Web Text))

Max Activating Token Index: 850

Text #6

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1141. Min Act: -0.0003

Data Index: 81992 (C4 (Web Text))

Max Activating Token Index: 49

Text #7

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1149. Min Act: -0.0003

Data Index: 535206 (C4 (Web Text))

Max Activating Token Index: 250

Text #8

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1117. Min Act: -0.0002

Data Index: 1314685 (C4 (Web Text))

Max Activating Token Index: 694

Text #9

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1104. Min Act: -0.0002

Data Index: 87432 (C4 (Web Text))

Max Activating Token Index: 767

Text #10

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1144. Min Act: -0.0003

Data Index: 205680 (C4 (Web Text))

Max Activating Token Index: 997

Text #11

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1095. Min Act: -0.0002

Data Index: 18047 (C4 (Web Text))

Max Activating Token Index: 160

Text #12

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1079. Min Act: -0.0003

Data Index: 372931 (C4 (Web Text))

Max Activating Token Index: 378

Text #13

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1076. Min Act: -0.0003

Data Index: 607579 (C4 (Web Text))

Max Activating Token Index: 177

Text #14

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1074. Min Act: -0.0002

Data Index: 515028 (C4 (Web Text))

Max Activating Token Index: 125

Text #15

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1112. Min Act: -0.0002

Data Index: 776141 (C4 (Web Text))

Max Activating Token Index: 378

Text #16

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1045. Min Act: -0.0003

Data Index: 1060043 (C4 (Web Text))

Max Activating Token Index: 720

Text #17

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1027. Min Act: -0.0002

Data Index: 471127 (C4 (Web Text))

Max Activating Token Index: 1006

Text #18

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1063. Min Act: -0.0002

Data Index: 1311859 (C4 (Web Text))

Max Activating Token Index: 582

Text #19

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1048. Min Act: -0.0002

Data Index: 1057884 (C4 (Web Text))

Max Activating Token Index: 776