Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5622 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1326. Min Range: -0.1326

Max Act: 0.1326. Min Act: -0.0002

Data Index: 729703 (C4 (Web Text))

Max Activating Token Index: 33

Text #1

Max Range: 0.1326. Min Range: -0.1326

Max Act: 0.1279. Min Act: -0.0002

Data Index: 640906 (C4 (Web Text))

Max Activating Token Index: 192

Text #2

Max Range: 0.1326. Min Range: -0.1326

Max Act: 0.1180. Min Act: -0.0002

Data Index: 931918 (C4 (Web Text))

Max Activating Token Index: 132

Text #3

Max Range: 0.1326. Min Range: -0.1326

Max Act: 0.1163. Min Act: -0.0002

Data Index: 1285845 (C4 (Web Text))

Max Activating Token Index: 43

Text #4

Max Range: 0.1326. Min Range: -0.1326

Max Act: 0.1152. Min Act: -0.0002

Data Index: 226684 (C4 (Web Text))

Max Activating Token Index: 192

Text #5

Max Range: 0.1326. Min Range: -0.1326

Max Act: 0.1099. Min Act: -0.0002

Data Index: 1146977 (C4 (Web Text))

Max Activating Token Index: 165

Text #6

Max Range: 0.1326. Min Range: -0.1326

Max Act: 0.1046. Min Act: -0.0002

Data Index: 44216 (C4 (Web Text))

Max Activating Token Index: 810

Text #7

Max Range: 0.1326. Min Range: -0.1326

Max Act: 0.1085. Min Act: -0.0002

Data Index: 781241 (C4 (Web Text))

Max Activating Token Index: 131

Text #8

Max Range: 0.1326. Min Range: -0.1326

Max Act: 0.1069. Min Act: -0.0002

Data Index: 167029 (C4 (Web Text))

Max Activating Token Index: 922

Text #9

Max Range: 0.1326. Min Range: -0.1326

Max Act: 0.1103. Min Act: -0.0002

Data Index: 243460 (C4 (Web Text))

Max Activating Token Index: 840

Text #10

Max Range: 0.1326. Min Range: -0.1326

Max Act: 0.1034. Min Act: -0.0002

Data Index: 480694 (C4 (Web Text))

Max Activating Token Index: 639

Text #11

Max Range: 0.1326. Min Range: -0.1326

Max Act: 0.1068. Min Act: -0.0002

Data Index: 839950 (C4 (Web Text))

Max Activating Token Index: 709

Text #12

Max Range: 0.1326. Min Range: -0.1326

Max Act: 0.1002. Min Act: -0.0002

Data Index: 394506 (C4 (Web Text))

Max Activating Token Index: 183

Text #13

Max Range: 0.1326. Min Range: -0.1326

Max Act: 0.1030. Min Act: -0.0002

Data Index: 478752 (C4 (Web Text))

Max Activating Token Index: 39

Text #14

Max Range: 0.1326. Min Range: -0.1326

Max Act: 0.1025. Min Act: -0.0002

Data Index: 181087 (C4 (Web Text))

Max Activating Token Index: 695

Text #15

Max Range: 0.1326. Min Range: -0.1326

Max Act: 0.1028. Min Act: -0.0002

Data Index: 1147847 (C4 (Web Text))

Max Activating Token Index: 529

Text #16

Max Range: 0.1326. Min Range: -0.1326

Max Act: 0.1005. Min Act: -0.0002

Data Index: 1029065 (C4 (Web Text))

Max Activating Token Index: 115

Text #17

Max Range: 0.1326. Min Range: -0.1326

Max Act: 0.1008. Min Act: -0.0002

Data Index: 837486 (C4 (Web Text))

Max Activating Token Index: 588

Text #18

Max Range: 0.1326. Min Range: -0.1326

Max Act: 0.0966. Min Act: -0.0002

Data Index: 119570 (C4 (Web Text))

Max Activating Token Index: 868

Text #19

Max Range: 0.1326. Min Range: -0.1326

Max Act: 0.0989. Min Act: -0.0002

Data Index: 305655 (C4 (Web Text))

Max Activating Token Index: 33