Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3945 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1235. Min Range: -0.1235

Max Act: 0.1235. Min Act: -0.0003

Data Index: 867431 (C4 (Web Text))

Max Activating Token Index: 62

Text #1

Max Range: 0.1235. Min Range: -0.1235

Max Act: 0.1172. Min Act: -0.0002

Data Index: 187052 (C4 (Web Text))

Max Activating Token Index: 131

Text #2

Max Range: 0.1235. Min Range: -0.1235

Max Act: 0.1143. Min Act: -0.0003

Data Index: 1220915 (C4 (Web Text))

Max Activating Token Index: 228

Text #3

Max Range: 0.1235. Min Range: -0.1235

Max Act: 0.1130. Min Act: -0.0002

Data Index: 779220 (C4 (Web Text))

Max Activating Token Index: 47

Text #4

Max Range: 0.1235. Min Range: -0.1235

Max Act: 0.1094. Min Act: -0.0003

Data Index: 926458 (C4 (Web Text))

Max Activating Token Index: 551

Text #5

Max Range: 0.1235. Min Range: -0.1235

Max Act: 0.1125. Min Act: -0.0003

Data Index: 428298 (C4 (Web Text))

Max Activating Token Index: 429

Text #6

Max Range: 0.1235. Min Range: -0.1235

Max Act: 0.1097. Min Act: -0.0003

Data Index: 166457 (C4 (Web Text))

Max Activating Token Index: 161

Text #7

Max Range: 0.1235. Min Range: -0.1235

Max Act: 0.1088. Min Act: -0.0003

Data Index: 291764 (C4 (Web Text))

Max Activating Token Index: 296

Text #8

Max Range: 0.1235. Min Range: -0.1235

Max Act: 0.1093. Min Act: -0.0003

Data Index: 947461 (C4 (Web Text))

Max Activating Token Index: 30

Text #9

Max Range: 0.1235. Min Range: -0.1235

Max Act: 0.1124. Min Act: -0.0003

Data Index: 38485 (C4 (Web Text))

Max Activating Token Index: 454

Text #10

Max Range: 0.1235. Min Range: -0.1235

Max Act: 0.1048. Min Act: -0.0003

Data Index: 584097 (C4 (Web Text))

Max Activating Token Index: 308

Text #11

Max Range: 0.1235. Min Range: -0.1235

Max Act: 0.1077. Min Act: -0.0003

Data Index: 768724 (C4 (Web Text))

Max Activating Token Index: 672

Text #12

Max Range: 0.1235. Min Range: -0.1235

Max Act: 0.1071. Min Act: -0.0003

Data Index: 439567 (C4 (Web Text))

Max Activating Token Index: 417

Text #13

Max Range: 0.1235. Min Range: -0.1235

Max Act: 0.1027. Min Act: -0.0003

Data Index: 749324 (C4 (Web Text))

Max Activating Token Index: 744

Text #14

Max Range: 0.1235. Min Range: -0.1235

Max Act: 0.1059. Min Act: -0.0003

Data Index: 1264026 (C4 (Web Text))

Max Activating Token Index: 583

Text #15

Max Range: 0.1235. Min Range: -0.1235

Max Act: 0.1011. Min Act: -0.0003

Data Index: 939869 (C4 (Web Text))

Max Activating Token Index: 193

Text #16

Max Range: 0.1235. Min Range: -0.1235

Max Act: 0.1036. Min Act: -0.0003

Data Index: 1199175 (C4 (Web Text))

Max Activating Token Index: 750

Text #17

Max Range: 0.1235. Min Range: -0.1235

Max Act: 0.1030. Min Act: -0.0002

Data Index: 470053 (C4 (Web Text))

Max Activating Token Index: 951

Text #18

Max Range: 0.1235. Min Range: -0.1235

Max Act: 0.1012. Min Act: -0.0003

Data Index: 956420 (C4 (Web Text))

Max Activating Token Index: 426

Text #19

Max Range: 0.1235. Min Range: -0.1235

Max Act: 0.1021. Min Act: -0.0003

Data Index: 440465 (C4 (Web Text))

Max Activating Token Index: 784