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

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

Neuron 2692 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1542. Min Range: -0.1542

Max Act: 0.1542. Min Act: -0.0003

Data Index: 990907 (C4 (Web Text))

Max Activating Token Index: 136

Text #1

Max Range: 0.1542. Min Range: -0.1542

Max Act: 0.1112. Min Act: -0.0003

Data Index: 240265 (C4 (Web Text))

Max Activating Token Index: 220

Text #2

Max Range: 0.1542. Min Range: -0.1542

Max Act: 0.1076. Min Act: -0.0003

Data Index: 377695 (C4 (Web Text))

Max Activating Token Index: 1008

Text #3

Max Range: 0.1542. Min Range: -0.1542

Max Act: 0.1027. Min Act: -0.0003

Data Index: 106103 (C4 (Web Text))

Max Activating Token Index: 983

Text #4

Max Range: 0.1542. Min Range: -0.1542

Max Act: 0.1071. Min Act: -0.0003

Data Index: 363765 (C4 (Web Text))

Max Activating Token Index: 221

Text #5

Max Range: 0.1542. Min Range: -0.1542

Max Act: 0.1054. Min Act: -0.0003

Data Index: 481810 (C4 (Web Text))

Max Activating Token Index: 97

Text #6

Max Range: 0.1542. Min Range: -0.1542

Max Act: 0.1139. Min Act: -0.0003

Data Index: 1057646 (C4 (Web Text))

Max Activating Token Index: 177

Text #7

Max Range: 0.1542. Min Range: -0.1542

Max Act: 0.1178. Min Act: -0.0003

Data Index: 1200262 (C4 (Web Text))

Max Activating Token Index: 873

Text #8

Max Range: 0.1542. Min Range: -0.1542

Max Act: 0.1001. Min Act: -0.0003

Data Index: 146139 (C4 (Web Text))

Max Activating Token Index: 959

Text #9

Max Range: 0.1542. Min Range: -0.1542

Max Act: 0.1029. Min Act: -0.0003

Data Index: 742541 (C4 (Web Text))

Max Activating Token Index: 51

Text #10

Max Range: 0.1542. Min Range: -0.1542

Max Act: 0.0910. Min Act: -0.0003

Data Index: 1028363 (C4 (Web Text))

Max Activating Token Index: 832

Text #11

Max Range: 0.1542. Min Range: -0.1542

Max Act: 0.1034. Min Act: -0.0003

Data Index: 1225034 (C4 (Web Text))

Max Activating Token Index: 231

Text #12

Max Range: 0.1542. Min Range: -0.1542

Max Act: 0.1110. Min Act: -0.0003

Data Index: 1315665 (C4 (Web Text))

Max Activating Token Index: 567

Text #13

Max Range: 0.1542. Min Range: -0.1542

Max Act: 0.0958. Min Act: -0.0003

Data Index: 90373 (C4 (Web Text))

Max Activating Token Index: 270

Text #14

Max Range: 0.1542. Min Range: -0.1542

Max Act: 0.1075. Min Act: -0.0003

Data Index: 30961 (C4 (Web Text))

Max Activating Token Index: 221

Text #15

Max Range: 0.1542. Min Range: -0.1542

Max Act: 0.1076. Min Act: -0.0003

Data Index: 37502 (C4 (Web Text))

Max Activating Token Index: 332

Text #16

Max Range: 0.1542. Min Range: -0.1542

Max Act: 0.1104. Min Act: -0.0003

Data Index: 467062 (C4 (Web Text))

Max Activating Token Index: 879

Text #17

Max Range: 0.1542. Min Range: -0.1542

Max Act: 0.1111. Min Act: -0.0003

Data Index: 1183288 (C4 (Web Text))

Max Activating Token Index: 195

Text #18

Max Range: 0.1542. Min Range: -0.1542

Max Act: 0.0939. Min Act: -0.0003

Data Index: 42244 (C4 (Web Text))

Max Activating Token Index: 254

Text #19

Max Range: 0.1542. Min Range: -0.1542

Max Act: 0.0964. Min Act: -0.0003

Data Index: 1322585 (C4 (Web Text))

Max Activating Token Index: 879