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

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

Neuron 1947 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: 0.1245. Min Range: -0.1245

Max Act: 0.1245. Min Act: -0.0003

Data Index: 253229 (C4 (Web Text))

Max Activating Token Index: 57

Text #1

Max Range: 0.1245. Min Range: -0.1245

Max Act: 0.1192. Min Act: -0.0003

Data Index: 261406 (C4 (Web Text))

Max Activating Token Index: 38

Text #2

Max Range: 0.1245. Min Range: -0.1245

Max Act: 0.1107. Min Act: -0.0002

Data Index: 80258 (C4 (Web Text))

Max Activating Token Index: 98

Text #3

Max Range: 0.1245. Min Range: -0.1245

Max Act: 0.1068. Min Act: -0.0003

Data Index: 484895 (C4 (Web Text))

Max Activating Token Index: 190

Text #4

Max Range: 0.1245. Min Range: -0.1245

Max Act: 0.1017. Min Act: -0.0003

Data Index: 723663 (C4 (Web Text))

Max Activating Token Index: 153

Text #5

Max Range: 0.1245. Min Range: -0.1245

Max Act: 0.1036. Min Act: -0.0003

Data Index: 1296060 (C4 (Web Text))

Max Activating Token Index: 23

Text #6

Max Range: 0.1245. Min Range: -0.1245

Max Act: 0.0935. Min Act: -0.0003

Data Index: 368826 (C4 (Web Text))

Max Activating Token Index: 675

Text #7

Max Range: 0.1245. Min Range: -0.1245

Max Act: 0.1046. Min Act: -0.0003

Data Index: 550280 (C4 (Web Text))

Max Activating Token Index: 22

Text #8

Max Range: 0.1245. Min Range: -0.1245

Max Act: 0.0972. Min Act: -0.0003

Data Index: 661473 (C4 (Web Text))

Max Activating Token Index: 664

Text #9

Max Range: 0.1245. Min Range: -0.1245

Max Act: 0.0978. Min Act: -0.0003

Data Index: 305580 (C4 (Web Text))

Max Activating Token Index: 805

Text #10

Max Range: 0.1245. Min Range: -0.1245

Max Act: 0.0990. Min Act: -0.0003

Data Index: 239005 (C4 (Web Text))

Max Activating Token Index: 600

Text #11

Max Range: 0.1245. Min Range: -0.1245

Max Act: 0.0977. Min Act: -0.0003

Data Index: 345097 (C4 (Web Text))

Max Activating Token Index: 160

Text #12

Max Range: 0.1245. Min Range: -0.1245

Max Act: 0.0921. Min Act: -0.0003

Data Index: 1066931 (C4 (Web Text))

Max Activating Token Index: 424

Text #13

Max Range: 0.1245. Min Range: -0.1245

Max Act: 0.0936. Min Act: -0.0003

Data Index: 633501 (C4 (Web Text))

Max Activating Token Index: 597

Text #14

Max Range: 0.1245. Min Range: -0.1245

Max Act: 0.0940. Min Act: -0.0003

Data Index: 943411 (C4 (Web Text))

Max Activating Token Index: 542

Text #15

Max Range: 0.1245. Min Range: -0.1245

Max Act: 0.0955. Min Act: -0.0003

Data Index: 463041 (C4 (Web Text))

Max Activating Token Index: 455

Text #16

Max Range: 0.1245. Min Range: -0.1245

Max Act: 0.0865. Min Act: -0.0003

Data Index: 1316185 (C4 (Web Text))

Max Activating Token Index: 733

Text #17

Max Range: 0.1245. Min Range: -0.1245

Max Act: 0.0880. Min Act: -0.0003

Data Index: 1134392 (C4 (Web Text))

Max Activating Token Index: 287

Text #18

Max Range: 0.1245. Min Range: -0.1245

Max Act: 0.0833. Min Act: -0.0002

Data Index: 752667 (C4 (Web Text))

Max Activating Token Index: 825

Text #19

Max Range: 0.1245. Min Range: -0.1245

Max Act: 0.0840. Min Act: -0.0003

Data Index: 1268043 (C4 (Web Text))

Max Activating Token Index: 233