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

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

Neuron 1736 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.1170. Min Act: -0.0006

Data Index: 970697 (C4 (Web Text))

Max Activating Token Index: 213

Text #1

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.1145. Min Act: -0.0006

Data Index: 917916 (C4 (Web Text))

Max Activating Token Index: 45

Text #2

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.1135. Min Act: -0.0006

Data Index: 42850 (C4 (Web Text))

Max Activating Token Index: 996

Text #3

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.1117. Min Act: -0.0006

Data Index: 469234 (C4 (Web Text))

Max Activating Token Index: 856

Text #4

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.1104. Min Act: -0.0006

Data Index: 1231098 (C4 (Web Text))

Max Activating Token Index: 977

Text #5

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.1071. Min Act: -0.0006

Data Index: 1289641 (C4 (Web Text))

Max Activating Token Index: 163

Text #6

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.1065. Min Act: -0.0005

Data Index: 955030 (C4 (Web Text))

Max Activating Token Index: 39

Text #7

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.1053. Min Act: -0.0005

Data Index: 433571 (C4 (Web Text))

Max Activating Token Index: 36

Text #8

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.1032. Min Act: -0.0005

Data Index: 305059 (C4 (Web Text))

Max Activating Token Index: 191

Text #9

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.1029. Min Act: -0.0006

Data Index: 864840 (C4 (Web Text))

Max Activating Token Index: 548

Text #10

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.1047. Min Act: -0.0006

Data Index: 1178767 (C4 (Web Text))

Max Activating Token Index: 23

Text #11

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.1019. Min Act: -0.0005

Data Index: 264353 (C4 (Web Text))

Max Activating Token Index: 309

Text #12

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0976. Min Act: -0.0006

Data Index: 1238263 (C4 (Web Text))

Max Activating Token Index: 880

Text #13

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.1050. Min Act: -0.0005

Data Index: 1132196 (C4 (Web Text))

Max Activating Token Index: 661

Text #14

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.1003. Min Act: -0.0005

Data Index: 119578 (C4 (Web Text))

Max Activating Token Index: 499

Text #15

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0999. Min Act: -0.0006

Data Index: 762758 (C4 (Web Text))

Max Activating Token Index: 68

Text #16

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0997. Min Act: -0.0006

Data Index: 211951 (C4 (Web Text))

Max Activating Token Index: 13

Text #17

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0978. Min Act: -0.0006

Data Index: 598753 (C4 (Web Text))

Max Activating Token Index: 807

Text #18

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0978. Min Act: -0.0006

Data Index: 404142 (C4 (Web Text))

Max Activating Token Index: 771

Text #19

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0993. Min Act: -0.0006

Data Index: 360877 (C4 (Web Text))

Max Activating Token Index: 871