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

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

Neuron 175 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: 0.1082. Min Range: -0.1082

Max Act: 0.1082. Min Act: -0.0003

Data Index: 779646 (C4 (Web Text))

Max Activating Token Index: 598

Text #1

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.1067. Min Act: -0.0003

Data Index: 1198249 (C4 (Web Text))

Max Activating Token Index: 77

Text #2

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.1056. Min Act: -0.0004

Data Index: 1356286 (C4 (Web Text))

Max Activating Token Index: 64

Text #3

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0996. Min Act: -0.0003

Data Index: 667133 (C4 (Web Text))

Max Activating Token Index: 677

Text #4

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.1065. Min Act: -0.0003

Data Index: 336399 (C4 (Web Text))

Max Activating Token Index: 825

Text #5

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.1038. Min Act: -0.0004

Data Index: 939813 (C4 (Web Text))

Max Activating Token Index: 168

Text #6

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.1053. Min Act: -0.0003

Data Index: 396794 (C4 (Web Text))

Max Activating Token Index: 13

Text #7

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.1053. Min Act: -0.0003

Data Index: 200232 (C4 (Web Text))

Max Activating Token Index: 13

Text #8

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.1031. Min Act: -0.0003

Data Index: 564847 (C4 (Web Text))

Max Activating Token Index: 12

Text #9

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.1031. Min Act: -0.0003

Data Index: 458723 (C4 (Web Text))

Max Activating Token Index: 12

Text #10

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.1046. Min Act: -0.0003

Data Index: 848322 (C4 (Web Text))

Max Activating Token Index: 13

Text #11

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0973. Min Act: -0.0003

Data Index: 1199954 (C4 (Web Text))

Max Activating Token Index: 946

Text #12

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.1049. Min Act: -0.0003

Data Index: 700998 (C4 (Web Text))

Max Activating Token Index: 491

Text #13

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.1029. Min Act: -0.0003

Data Index: 1125795 (C4 (Web Text))

Max Activating Token Index: 675

Text #14

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.1040. Min Act: -0.0003

Data Index: 937617 (C4 (Web Text))

Max Activating Token Index: 1012

Text #15

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.1033. Min Act: -0.0004

Data Index: 451594 (C4 (Web Text))

Max Activating Token Index: 245

Text #16

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.1079. Min Act: -0.0004

Data Index: 1295179 (C4 (Web Text))

Max Activating Token Index: 810

Text #17

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0995. Min Act: -0.0003

Data Index: 474497 (C4 (Web Text))

Max Activating Token Index: 808

Text #18

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.1063. Min Act: -0.0003

Data Index: 304458 (C4 (Web Text))

Max Activating Token Index: 155

Text #19

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.1023. Min Act: -0.0004

Data Index: 577643 (C4 (Web Text))

Max Activating Token Index: 17