Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3574 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0852. Min Act: -0.0002

Data Index: 774970 (C4 (Web Text))

Max Activating Token Index: 241

Text #1

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0842. Min Act: -0.0002

Data Index: 958389 (C4 (Web Text))

Max Activating Token Index: 4

Text #2

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0790. Min Act: -0.0002

Data Index: 617634 (C4 (Web Text))

Max Activating Token Index: 646

Text #3

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0769. Min Act: -0.0002

Data Index: 267160 (C4 (Web Text))

Max Activating Token Index: 50

Text #4

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0776. Min Act: -0.0002

Data Index: 1055855 (C4 (Web Text))

Max Activating Token Index: 694

Text #5

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0754. Min Act: -0.0002

Data Index: 197764 (C4 (Web Text))

Max Activating Token Index: 218

Text #6

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0725. Min Act: -0.0002

Data Index: 67450 (C4 (Web Text))

Max Activating Token Index: 694

Text #7

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0715. Min Act: -0.0002

Data Index: 921946 (C4 (Web Text))

Max Activating Token Index: 344

Text #8

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0679. Min Act: -0.0002

Data Index: 389442 (C4 (Web Text))

Max Activating Token Index: 33

Text #9

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0737. Min Act: -0.0002

Data Index: 932131 (C4 (Web Text))

Max Activating Token Index: 383

Text #10

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0715. Min Act: -0.0002

Data Index: 1248856 (C4 (Web Text))

Max Activating Token Index: 26

Text #11

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0684. Min Act: -0.0002

Data Index: 1086725 (C4 (Web Text))

Max Activating Token Index: 281

Text #12

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0669. Min Act: -0.0002

Data Index: 676551 (C4 (Web Text))

Max Activating Token Index: 678

Text #13

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0711. Min Act: -0.0002

Data Index: 295254 (C4 (Web Text))

Max Activating Token Index: 897

Text #14

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0684. Min Act: -0.0002

Data Index: 192032 (C4 (Web Text))

Max Activating Token Index: 399

Text #15

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0686. Min Act: -0.0002

Data Index: 727643 (C4 (Web Text))

Max Activating Token Index: 247

Text #16

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0670. Min Act: -0.0002

Data Index: 950944 (C4 (Web Text))

Max Activating Token Index: 807

Text #17

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0672. Min Act: -0.0002

Data Index: 291147 (C4 (Web Text))

Max Activating Token Index: 877

Text #18

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0664. Min Act: -0.0002

Data Index: 298992 (C4 (Web Text))

Max Activating Token Index: 47

Text #19

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0634. Min Act: -0.0002

Data Index: 211826 (C4 (Web Text))

Max Activating Token Index: 713