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

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

Neuron 31 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: 0.1251. Min Range: -0.1251

Max Act: 0.1251. Min Act: -0.0003

Data Index: 428143 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.1184. Min Act: -0.0003

Data Index: 81914 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.1235. Min Act: -0.0003

Data Index: 1145775 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.1164. Min Act: -0.0002

Data Index: 1109945 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.1133. Min Act: -0.0003

Data Index: 1022675 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.1121. Min Act: -0.0003

Data Index: 502639 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.1094. Min Act: -0.0003

Data Index: 43191 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.1094. Min Act: -0.0003

Data Index: 814065 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.1069. Min Act: -0.0003

Data Index: 19930 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.1049. Min Act: -0.0003

Data Index: 296306 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.1064. Min Act: -0.0003

Data Index: 105567 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.1008. Min Act: -0.0002

Data Index: 219692 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.1063. Min Act: -0.0003

Data Index: 163570 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.1049. Min Act: -0.0003

Data Index: 545771 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.1054. Min Act: -0.0003

Data Index: 442196 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.1112. Min Act: -0.0003

Data Index: 1172367 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.1064. Min Act: -0.0003

Data Index: 603209 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.1035. Min Act: -0.0003

Data Index: 1049825 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.1051. Min Act: -0.0004

Data Index: 568918 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.1039. Min Act: -0.0003

Data Index: 458074 (C4 (Web Text))

Max Activating Token Index: 1023