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

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

Neuron 999 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: 0.1260. Min Range: -0.1260

Max Act: 0.1260. Min Act: -0.0003

Data Index: 924502 (C4 (Web Text))

Max Activating Token Index: 1019

Text #1

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.1080. Min Act: -0.0003

Data Index: 1158739 (C4 (Web Text))

Max Activating Token Index: 875

Text #2

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.1069. Min Act: -0.0003

Data Index: 628466 (C4 (Web Text))

Max Activating Token Index: 675

Text #3

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.1097. Min Act: -0.0003

Data Index: 904377 (C4 (Web Text))

Max Activating Token Index: 660

Text #4

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.1100. Min Act: -0.0003

Data Index: 256318 (C4 (Web Text))

Max Activating Token Index: 501

Text #5

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.1071. Min Act: -0.0003

Data Index: 259629 (C4 (Web Text))

Max Activating Token Index: 256

Text #6

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.1134. Min Act: -0.0003

Data Index: 906185 (C4 (Web Text))

Max Activating Token Index: 826

Text #7

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.1062. Min Act: -0.0003

Data Index: 34969 (C4 (Web Text))

Max Activating Token Index: 890

Text #8

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.1056. Min Act: -0.0003

Data Index: 180137 (C4 (Web Text))

Max Activating Token Index: 149

Text #9

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.1099. Min Act: -0.0003

Data Index: 1002099 (C4 (Web Text))

Max Activating Token Index: 104

Text #10

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.1100. Min Act: -0.0003

Data Index: 365290 (C4 (Web Text))

Max Activating Token Index: 980

Text #11

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.1073. Min Act: -0.0003

Data Index: 690564 (C4 (Web Text))

Max Activating Token Index: 693

Text #12

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.1080. Min Act: -0.0003

Data Index: 45810 (C4 (Web Text))

Max Activating Token Index: 595

Text #13

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.1051. Min Act: -0.0003

Data Index: 1130037 (C4 (Web Text))

Max Activating Token Index: 921

Text #14

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.1077. Min Act: -0.0002

Data Index: 1309814 (C4 (Web Text))

Max Activating Token Index: 869

Text #15

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.1078. Min Act: -0.0003

Data Index: 680341 (C4 (Web Text))

Max Activating Token Index: 269

Text #16

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.1065. Min Act: -0.0003

Data Index: 895971 (C4 (Web Text))

Max Activating Token Index: 892

Text #17

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.1077. Min Act: -0.0002

Data Index: 345383 (C4 (Web Text))

Max Activating Token Index: 991

Text #18

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.1041. Min Act: -0.0003

Data Index: 457983 (C4 (Web Text))

Max Activating Token Index: 529

Text #19

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.1088. Min Act: -0.0003

Data Index: 295549 (C4 (Web Text))

Max Activating Token Index: 95