Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 41 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0980. Min Act: -0.0002

Data Index: 1226907 (C4 (Web Text))

Max Activating Token Index: 653

Text #1

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0789. Min Act: -0.0002

Data Index: 651218 (C4 (Web Text))

Max Activating Token Index: 406

Text #2

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0772. Min Act: -0.0002

Data Index: 255715 (C4 (Web Text))

Max Activating Token Index: 966

Text #3

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0759. Min Act: -0.0002

Data Index: 242863 (C4 (Web Text))

Max Activating Token Index: 249

Text #4

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0783. Min Act: -0.0002

Data Index: 1159962 (C4 (Web Text))

Max Activating Token Index: 716

Text #5

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0769. Min Act: -0.0002

Data Index: 480004 (C4 (Web Text))

Max Activating Token Index: 687

Text #6

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0729. Min Act: -0.0002

Data Index: 157076 (C4 (Web Text))

Max Activating Token Index: 279

Text #7

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0768. Min Act: -0.0002

Data Index: 1215185 (C4 (Web Text))

Max Activating Token Index: 138

Text #8

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0777. Min Act: -0.0002

Data Index: 713169 (C4 (Web Text))

Max Activating Token Index: 121

Text #9

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0756. Min Act: -0.0002

Data Index: 1115282 (C4 (Web Text))

Max Activating Token Index: 137

Text #10

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0761. Min Act: -0.0002

Data Index: 1023793 (C4 (Web Text))

Max Activating Token Index: 242

Text #11

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0766. Min Act: -0.0002

Data Index: 494799 (C4 (Web Text))

Max Activating Token Index: 1015

Text #12

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0732. Min Act: -0.0002

Data Index: 336822 (C4 (Web Text))

Max Activating Token Index: 164

Text #13

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0745. Min Act: -0.0002

Data Index: 280458 (C4 (Web Text))

Max Activating Token Index: 661

Text #14

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0727. Min Act: -0.0002

Data Index: 1096152 (C4 (Web Text))

Max Activating Token Index: 627

Text #15

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0761. Min Act: -0.0002

Data Index: 66362 (C4 (Web Text))

Max Activating Token Index: 223

Text #16

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0745. Min Act: -0.0002

Data Index: 189716 (C4 (Web Text))

Max Activating Token Index: 197

Text #17

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0747. Min Act: -0.0002

Data Index: 1291091 (C4 (Web Text))

Max Activating Token Index: 890

Text #18

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0750. Min Act: -0.0002

Data Index: 850540 (C4 (Web Text))

Max Activating Token Index: 869

Text #19

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0730. Min Act: -0.0002

Data Index: 1177436 (C4 (Web Text))

Max Activating Token Index: 374