Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1103 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1255. Min Range: -0.1255

Max Act: 0.1178. Min Act: -0.0001

Data Index: 1153850 (C4 (Web Text))

Max Activating Token Index: 752

Text #1

Max Range: 0.1255. Min Range: -0.1255

Max Act: 0.1255. Min Act: -0.0002

Data Index: 73726 (C4 (Web Text))

Max Activating Token Index: 259

Text #2

Max Range: 0.1255. Min Range: -0.1255

Max Act: 0.1199. Min Act: -0.0001

Data Index: 327226 (C4 (Web Text))

Max Activating Token Index: 138

Text #3

Max Range: 0.1255. Min Range: -0.1255

Max Act: 0.1203. Min Act: -0.0000

Data Index: 1053913 (C4 (Web Text))

Max Activating Token Index: 965

Text #4

Max Range: 0.1255. Min Range: -0.1255

Max Act: 0.1209. Min Act: -0.0001

Data Index: 133135 (C4 (Web Text))

Max Activating Token Index: 685

Text #5

Max Range: 0.1255. Min Range: -0.1255

Max Act: 0.1113. Min Act: -0.0001

Data Index: 1325982 (C4 (Web Text))

Max Activating Token Index: 926

Text #6

Max Range: 0.1255. Min Range: -0.1255

Max Act: 0.1139. Min Act: -0.0000

Data Index: 1287208 (C4 (Web Text))

Max Activating Token Index: 800

Text #7

Max Range: 0.1255. Min Range: -0.1255

Max Act: 0.1046. Min Act: -0.0001

Data Index: 1248665 (C4 (Web Text))

Max Activating Token Index: 621

Text #8

Max Range: 0.1255. Min Range: -0.1255

Max Act: 0.1064. Min Act: -0.0001

Data Index: 383632 (C4 (Web Text))

Max Activating Token Index: 780

Text #9

Max Range: 0.1255. Min Range: -0.1255

Max Act: 0.1094. Min Act: -0.0001

Data Index: 403279 (C4 (Web Text))

Max Activating Token Index: 397

Text #10

Max Range: 0.1255. Min Range: -0.1255

Max Act: 0.1048. Min Act: -0.0001

Data Index: 311600 (C4 (Web Text))

Max Activating Token Index: 92

Text #11

Max Range: 0.1255. Min Range: -0.1255

Max Act: 0.1082. Min Act: -0.0001

Data Index: 1256070 (C4 (Web Text))

Max Activating Token Index: 91

Text #12

Max Range: 0.1255. Min Range: -0.1255

Max Act: 0.1072. Min Act: -0.0002

Data Index: 823052 (C4 (Web Text))

Max Activating Token Index: 279

Text #13

Max Range: 0.1255. Min Range: -0.1255

Max Act: 0.1047. Min Act: -0.0002

Data Index: 1059974 (C4 (Web Text))

Max Activating Token Index: 313

Text #14

Max Range: 0.1255. Min Range: -0.1255

Max Act: 0.1044. Min Act: -0.0001

Data Index: 254087 (C4 (Web Text))

Max Activating Token Index: 739

Text #15

Max Range: 0.1255. Min Range: -0.1255

Max Act: 0.1035. Min Act: -0.0000

Data Index: 591521 (C4 (Web Text))

Max Activating Token Index: 483

Text #16

Max Range: 0.1255. Min Range: -0.1255

Max Act: 0.1075. Min Act: -0.0001

Data Index: 548994 (C4 (Web Text))

Max Activating Token Index: 1004

Text #17

Max Range: 0.1255. Min Range: -0.1255

Max Act: 0.1012. Min Act: -0.0001

Data Index: 626754 (C4 (Web Text))

Max Activating Token Index: 827

Text #18

Max Range: 0.1255. Min Range: -0.1255

Max Act: 0.1066. Min Act: -0.0001

Data Index: 462546 (C4 (Web Text))

Max Activating Token Index: 875

Text #19

Max Range: 0.1255. Min Range: -0.1255

Max Act: 0.1031. Min Act: -0.0001

Data Index: 1017755 (C4 (Web Text))

Max Activating Token Index: 945