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

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

Neuron 4561 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1697. Min Range: -0.1697

Max Act: 0.1697. Min Act: -0.0000

Data Index: 357029 (C4 (Web Text))

Max Activating Token Index: 644

Text #1

Max Range: 0.1697. Min Range: -0.1697

Max Act: 0.1260. Min Act: -0.0000

Data Index: 817814 (C4 (Web Text))

Max Activating Token Index: 709

Text #2

Max Range: 0.1697. Min Range: -0.1697

Max Act: 0.1147. Min Act: -0.0000

Data Index: 995411 (C4 (Web Text))

Max Activating Token Index: 277

Text #3

Max Range: 0.1697. Min Range: -0.1697

Max Act: 0.1106. Min Act: -0.0000

Data Index: 735747 (C4 (Web Text))

Max Activating Token Index: 86

Text #4

Max Range: 0.1697. Min Range: -0.1697

Max Act: 0.1098. Min Act: -0.0000

Data Index: 660781 (C4 (Web Text))

Max Activating Token Index: 354

Text #5

Max Range: 0.1697. Min Range: -0.1697

Max Act: 0.1124. Min Act: -0.0001

Data Index: 1143531 (C4 (Web Text))

Max Activating Token Index: 210

Text #6

Max Range: 0.1697. Min Range: -0.1697

Max Act: 0.1086. Min Act: -0.0000

Data Index: 1163165 (C4 (Web Text))

Max Activating Token Index: 921

Text #7

Max Range: 0.1697. Min Range: -0.1697

Max Act: 0.1045. Min Act: -0.0000

Data Index: 1070356 (C4 (Web Text))

Max Activating Token Index: 481

Text #8

Max Range: 0.1697. Min Range: -0.1697

Max Act: 0.1125. Min Act: -0.0000

Data Index: 542098 (C4 (Web Text))

Max Activating Token Index: 415

Text #9

Max Range: 0.1697. Min Range: -0.1697

Max Act: 0.1075. Min Act: -0.0000

Data Index: 744713 (C4 (Web Text))

Max Activating Token Index: 417

Text #10

Max Range: 0.1697. Min Range: -0.1697

Max Act: 0.1013. Min Act: -0.0000

Data Index: 185476 (C4 (Web Text))

Max Activating Token Index: 1007

Text #11

Max Range: 0.1697. Min Range: -0.1697

Max Act: 0.1104. Min Act: -0.0000

Data Index: 274751 (C4 (Web Text))

Max Activating Token Index: 81

Text #12

Max Range: 0.1697. Min Range: -0.1697

Max Act: 0.1047. Min Act: -0.0000

Data Index: 1237056 (C4 (Web Text))

Max Activating Token Index: 288

Text #13

Max Range: 0.1697. Min Range: -0.1697

Max Act: 0.1025. Min Act: -0.0000

Data Index: 1031939 (C4 (Web Text))

Max Activating Token Index: 401

Text #14

Max Range: 0.1697. Min Range: -0.1697

Max Act: 0.1039. Min Act: -0.0000

Data Index: 703367 (C4 (Web Text))

Max Activating Token Index: 1022

Text #15

Max Range: 0.1697. Min Range: -0.1697

Max Act: 0.1029. Min Act: -0.0000

Data Index: 557622 (C4 (Web Text))

Max Activating Token Index: 70

Text #16

Max Range: 0.1697. Min Range: -0.1697

Max Act: 0.1037. Min Act: -0.0000

Data Index: 1227899 (C4 (Web Text))

Max Activating Token Index: 912

Text #17

Max Range: 0.1697. Min Range: -0.1697

Max Act: 0.1012. Min Act: -0.0000

Data Index: 833296 (C4 (Web Text))

Max Activating Token Index: 859

Text #18

Max Range: 0.1697. Min Range: -0.1697

Max Act: 0.1054. Min Act: -0.0000

Data Index: 921180 (C4 (Web Text))

Max Activating Token Index: 541

Text #19

Max Range: 0.1697. Min Range: -0.1697

Max Act: 0.1020. Min Act: -0.0000

Data Index: 492253 (C4 (Web Text))

Max Activating Token Index: 209