Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4144 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.1204. Min Act: -0.0001

Data Index: 1092446 (C4 (Web Text))

Max Activating Token Index: 455

Text #1

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.1260. Min Act: -0.0001

Data Index: 1075186 (C4 (Web Text))

Max Activating Token Index: 1012

Text #2

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.1123. Min Act: -0.0001

Data Index: 117046 (C4 (Web Text))

Max Activating Token Index: 932

Text #3

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.1226. Min Act: -0.0001

Data Index: 465167 (C4 (Web Text))

Max Activating Token Index: 261

Text #4

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.1095. Min Act: -0.0001

Data Index: 403320 (C4 (Web Text))

Max Activating Token Index: 204

Text #5

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.1090. Min Act: -0.0001

Data Index: 236918 (C4 (Web Text))

Max Activating Token Index: 594

Text #6

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.1101. Min Act: -0.0001

Data Index: 810308 (C4 (Web Text))

Max Activating Token Index: 627

Text #7

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.1082. Min Act: -0.0001

Data Index: 828517 (C4 (Web Text))

Max Activating Token Index: 194

Text #8

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.1146. Min Act: -0.0001

Data Index: 49621 (C4 (Web Text))

Max Activating Token Index: 78

Text #9

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.1135. Min Act: -0.0001

Data Index: 765936 (C4 (Web Text))

Max Activating Token Index: 982

Text #10

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.1056. Min Act: -0.0001

Data Index: 961721 (C4 (Web Text))

Max Activating Token Index: 344

Text #11

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.1093. Min Act: -0.0001

Data Index: 594616 (C4 (Web Text))

Max Activating Token Index: 494

Text #12

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.1125. Min Act: -0.0001

Data Index: 1098602 (C4 (Web Text))

Max Activating Token Index: 872

Text #13

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.1046. Min Act: -0.0001

Data Index: 384290 (C4 (Web Text))

Max Activating Token Index: 760

Text #14

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.1103. Min Act: -0.0001

Data Index: 1273905 (C4 (Web Text))

Max Activating Token Index: 504

Text #15

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.1096. Min Act: -0.0001

Data Index: 1846 (C4 (Web Text))

Max Activating Token Index: 569

Text #16

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.1059. Min Act: -0.0001

Data Index: 1057253 (C4 (Web Text))

Max Activating Token Index: 595

Text #17

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.1017. Min Act: -0.0001

Data Index: 971099 (C4 (Web Text))

Max Activating Token Index: 768

Text #18

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.1047. Min Act: -0.0001

Data Index: 652320 (C4 (Web Text))

Max Activating Token Index: 650

Text #19

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.1043. Min Act: -0.0001

Data Index: 977063 (C4 (Web Text))

Max Activating Token Index: 320