Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1694 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1248. Min Range: -0.1248

Max Act: 0.1248. Min Act: -0.0000

Data Index: 626456 (C4 (Web Text))

Max Activating Token Index: 997

Text #1

Max Range: 0.1248. Min Range: -0.1248

Max Act: 0.1223. Min Act: -0.0001

Data Index: 573924 (C4 (Web Text))

Max Activating Token Index: 601

Text #2

Max Range: 0.1248. Min Range: -0.1248

Max Act: 0.1226. Min Act: -0.0000

Data Index: 857631 (C4 (Web Text))

Max Activating Token Index: 29

Text #3

Max Range: 0.1248. Min Range: -0.1248

Max Act: 0.1148. Min Act: -0.0001

Data Index: 470062 (C4 (Web Text))

Max Activating Token Index: 254

Text #4

Max Range: 0.1248. Min Range: -0.1248

Max Act: 0.1211. Min Act: -0.0000

Data Index: 975015 (C4 (Web Text))

Max Activating Token Index: 475

Text #5

Max Range: 0.1248. Min Range: -0.1248

Max Act: 0.1107. Min Act: -0.0000

Data Index: 118292 (C4 (Web Text))

Max Activating Token Index: 1018

Text #6

Max Range: 0.1248. Min Range: -0.1248

Max Act: 0.1185. Min Act: -0.0000

Data Index: 754506 (C4 (Web Text))

Max Activating Token Index: 229

Text #7

Max Range: 0.1248. Min Range: -0.1248

Max Act: 0.1089. Min Act: -0.0000

Data Index: 1240473 (C4 (Web Text))

Max Activating Token Index: 106

Text #8

Max Range: 0.1248. Min Range: -0.1248

Max Act: 0.1043. Min Act: -0.0001

Data Index: 153899 (C4 (Web Text))

Max Activating Token Index: 907

Text #9

Max Range: 0.1248. Min Range: -0.1248

Max Act: 0.1080. Min Act: -0.0000

Data Index: 1035112 (C4 (Web Text))

Max Activating Token Index: 258

Text #10

Max Range: 0.1248. Min Range: -0.1248

Max Act: 0.1074. Min Act: -0.0000

Data Index: 984753 (C4 (Web Text))

Max Activating Token Index: 460

Text #11

Max Range: 0.1248. Min Range: -0.1248

Max Act: 0.1071. Min Act: -0.0001

Data Index: 113766 (C4 (Web Text))

Max Activating Token Index: 670

Text #12

Max Range: 0.1248. Min Range: -0.1248

Max Act: 0.1064. Min Act: -0.0000

Data Index: 849259 (C4 (Web Text))

Max Activating Token Index: 119

Text #13

Max Range: 0.1248. Min Range: -0.1248

Max Act: 0.1030. Min Act: -0.0000

Data Index: 1163157 (C4 (Web Text))

Max Activating Token Index: 74

Text #14

Max Range: 0.1248. Min Range: -0.1248

Max Act: 0.1026. Min Act: -0.0001

Data Index: 666021 (C4 (Web Text))

Max Activating Token Index: 487

Text #15

Max Range: 0.1248. Min Range: -0.1248

Max Act: 0.1058. Min Act: -0.0000

Data Index: 1016859 (C4 (Web Text))

Max Activating Token Index: 839

Text #16

Max Range: 0.1248. Min Range: -0.1248

Max Act: 0.1042. Min Act: -0.0001

Data Index: 234145 (C4 (Web Text))

Max Activating Token Index: 269

Text #17

Max Range: 0.1248. Min Range: -0.1248

Max Act: 0.1051. Min Act: -0.0000

Data Index: 1200275 (C4 (Web Text))

Max Activating Token Index: 973

Text #18

Max Range: 0.1248. Min Range: -0.1248

Max Act: 0.1013. Min Act: -0.0000

Data Index: 340965 (C4 (Web Text))

Max Activating Token Index: 212

Text #19

Max Range: 0.1248. Min Range: -0.1248

Max Act: 0.1041. Min Act: -0.0000

Data Index: 356393 (C4 (Web Text))

Max Activating Token Index: 192