Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1410 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1077. Min Range: -0.1077

Max Act: 0.1077. Min Act: -0.0003

Data Index: 695056 (C4 (Web Text))

Max Activating Token Index: 45

Text #1

Max Range: 0.1077. Min Range: -0.1077

Max Act: 0.0995. Min Act: -0.0003

Data Index: 836793 (C4 (Web Text))

Max Activating Token Index: 685

Text #2

Max Range: 0.1077. Min Range: -0.1077

Max Act: 0.1014. Min Act: -0.0003

Data Index: 107771 (C4 (Web Text))

Max Activating Token Index: 60

Text #3

Max Range: 0.1077. Min Range: -0.1077

Max Act: 0.1052. Min Act: -0.0003

Data Index: 330713 (C4 (Web Text))

Max Activating Token Index: 35

Text #4

Max Range: 0.1077. Min Range: -0.1077

Max Act: 0.1055. Min Act: -0.0003

Data Index: 1208588 (C4 (Web Text))

Max Activating Token Index: 158

Text #5

Max Range: 0.1077. Min Range: -0.1077

Max Act: 0.1051. Min Act: -0.0003

Data Index: 1185596 (C4 (Web Text))

Max Activating Token Index: 19

Text #6

Max Range: 0.1077. Min Range: -0.1077

Max Act: 0.1046. Min Act: -0.0003

Data Index: 522846 (C4 (Web Text))

Max Activating Token Index: 103

Text #7

Max Range: 0.1077. Min Range: -0.1077

Max Act: 0.0961. Min Act: -0.0003

Data Index: 152123 (C4 (Web Text))

Max Activating Token Index: 823

Text #8

Max Range: 0.1077. Min Range: -0.1077

Max Act: 0.1077. Min Act: -0.0003

Data Index: 477687 (C4 (Web Text))

Max Activating Token Index: 513

Text #9

Max Range: 0.1077. Min Range: -0.1077

Max Act: 0.1064. Min Act: -0.0003

Data Index: 1199101 (C4 (Web Text))

Max Activating Token Index: 204

Text #10

Max Range: 0.1077. Min Range: -0.1077

Max Act: 0.1034. Min Act: -0.0003

Data Index: 95751 (C4 (Web Text))

Max Activating Token Index: 54

Text #11

Max Range: 0.1077. Min Range: -0.1077

Max Act: 0.0956. Min Act: -0.0003

Data Index: 1348995 (C4 (Web Text))

Max Activating Token Index: 336

Text #12

Max Range: 0.1077. Min Range: -0.1077

Max Act: 0.1027. Min Act: -0.0003

Data Index: 325671 (C4 (Web Text))

Max Activating Token Index: 137

Text #13

Max Range: 0.1077. Min Range: -0.1077

Max Act: 0.0965. Min Act: -0.0003

Data Index: 602013 (C4 (Web Text))

Max Activating Token Index: 31

Text #14

Max Range: 0.1077. Min Range: -0.1077

Max Act: 0.0978. Min Act: -0.0003

Data Index: 124161 (C4 (Web Text))

Max Activating Token Index: 58

Text #15

Max Range: 0.1077. Min Range: -0.1077

Max Act: 0.0975. Min Act: -0.0003

Data Index: 766778 (C4 (Web Text))

Max Activating Token Index: 16

Text #16

Max Range: 0.1077. Min Range: -0.1077

Max Act: 0.1039. Min Act: -0.0003

Data Index: 948295 (C4 (Web Text))

Max Activating Token Index: 223

Text #17

Max Range: 0.1077. Min Range: -0.1077

Max Act: 0.0964. Min Act: -0.0003

Data Index: 765546 (C4 (Web Text))

Max Activating Token Index: 13

Text #18

Max Range: 0.1077. Min Range: -0.1077

Max Act: 0.1043. Min Act: -0.0003

Data Index: 186729 (C4 (Web Text))

Max Activating Token Index: 161

Text #19

Max Range: 0.1077. Min Range: -0.1077

Max Act: 0.0972. Min Act: -0.0003

Data Index: 1057160 (C4 (Web Text))

Max Activating Token Index: 291