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

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

Neuron 237 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.1158. Min Act: -0.0001

Data Index: 518392 (C4 (Web Text))

Max Activating Token Index: 769

Text #1

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.1145. Min Act: -0.0001

Data Index: 799653 (C4 (Web Text))

Max Activating Token Index: 220

Text #2

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.1142. Min Act: -0.0001

Data Index: 305466 (C4 (Web Text))

Max Activating Token Index: 559

Text #3

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.1059. Min Act: -0.0001

Data Index: 825271 (C4 (Web Text))

Max Activating Token Index: 55

Text #4

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.1055. Min Act: -0.0001

Data Index: 156930 (C4 (Web Text))

Max Activating Token Index: 784

Text #5

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.1056. Min Act: -0.0001

Data Index: 1324612 (C4 (Web Text))

Max Activating Token Index: 715

Text #6

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.1094. Min Act: -0.0001

Data Index: 936 (C4 (Web Text))

Max Activating Token Index: 203

Text #7

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.1078. Min Act: -0.0001

Data Index: 1005106 (C4 (Web Text))

Max Activating Token Index: 947

Text #8

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.1183. Min Act: -0.0001

Data Index: 753799 (C4 (Web Text))

Max Activating Token Index: 849

Text #9

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.1052. Min Act: -0.0001

Data Index: 1037083 (C4 (Web Text))

Max Activating Token Index: 458

Text #10

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.1092. Min Act: -0.0001

Data Index: 173151 (C4 (Web Text))

Max Activating Token Index: 907

Text #11

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.1013. Min Act: -0.0001

Data Index: 1240048 (C4 (Web Text))

Max Activating Token Index: 33

Text #12

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.1113. Min Act: -0.0001

Data Index: 1155946 (C4 (Web Text))

Max Activating Token Index: 176

Text #13

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.1035. Min Act: -0.0001

Data Index: 282579 (C4 (Web Text))

Max Activating Token Index: 485

Text #14

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.1023. Min Act: -0.0001

Data Index: 1210135 (C4 (Web Text))

Max Activating Token Index: 460

Text #15

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.1017. Min Act: -0.0001

Data Index: 479417 (C4 (Web Text))

Max Activating Token Index: 28

Text #16

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.0978. Min Act: -0.0001

Data Index: 983089 (C4 (Web Text))

Max Activating Token Index: 501

Text #17

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.0978. Min Act: -0.0001

Data Index: 1134530 (C4 (Web Text))

Max Activating Token Index: 87

Text #18

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.1016. Min Act: -0.0001

Data Index: 1024854 (C4 (Web Text))

Max Activating Token Index: 322

Text #19

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.1006. Min Act: -0.0001

Data Index: 612361 (C4 (Web Text))

Max Activating Token Index: 237