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

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

Neuron 1450 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: 0.0828. Min Range: -0.0828

Max Act: 0.0828. Min Act: -0.0002

Data Index: 693547 (C4 (Web Text))

Max Activating Token Index: 886

Text #1

Max Range: 0.0828. Min Range: -0.0828

Max Act: 0.0785. Min Act: -0.0002

Data Index: 93579 (C4 (Web Text))

Max Activating Token Index: 347

Text #2

Max Range: 0.0828. Min Range: -0.0828

Max Act: 0.0811. Min Act: -0.0002

Data Index: 970337 (C4 (Web Text))

Max Activating Token Index: 962

Text #3

Max Range: 0.0828. Min Range: -0.0828

Max Act: 0.0774. Min Act: -0.0002

Data Index: 171140 (C4 (Web Text))

Max Activating Token Index: 276

Text #4

Max Range: 0.0828. Min Range: -0.0828

Max Act: 0.0762. Min Act: -0.0002

Data Index: 1217649 (C4 (Web Text))

Max Activating Token Index: 587

Text #5

Max Range: 0.0828. Min Range: -0.0828

Max Act: 0.0765. Min Act: -0.0002

Data Index: 857201 (C4 (Web Text))

Max Activating Token Index: 120

Text #6

Max Range: 0.0828. Min Range: -0.0828

Max Act: 0.0729. Min Act: -0.0002

Data Index: 560719 (C4 (Web Text))

Max Activating Token Index: 794

Text #7

Max Range: 0.0828. Min Range: -0.0828

Max Act: 0.0754. Min Act: -0.0002

Data Index: 15903 (C4 (Web Text))

Max Activating Token Index: 69

Text #8

Max Range: 0.0828. Min Range: -0.0828

Max Act: 0.0742. Min Act: -0.0002

Data Index: 1352427 (C4 (Web Text))

Max Activating Token Index: 17

Text #9

Max Range: 0.0828. Min Range: -0.0828

Max Act: 0.0739. Min Act: -0.0002

Data Index: 896485 (C4 (Web Text))

Max Activating Token Index: 115

Text #10

Max Range: 0.0828. Min Range: -0.0828

Max Act: 0.0746. Min Act: -0.0002

Data Index: 353155 (C4 (Web Text))

Max Activating Token Index: 737

Text #11

Max Range: 0.0828. Min Range: -0.0828

Max Act: 0.0705. Min Act: -0.0002

Data Index: 221511 (C4 (Web Text))

Max Activating Token Index: 303

Text #12

Max Range: 0.0828. Min Range: -0.0828

Max Act: 0.0730. Min Act: -0.0002

Data Index: 670468 (C4 (Web Text))

Max Activating Token Index: 190

Text #13

Max Range: 0.0828. Min Range: -0.0828

Max Act: 0.0711. Min Act: -0.0002

Data Index: 571913 (C4 (Web Text))

Max Activating Token Index: 481

Text #14

Max Range: 0.0828. Min Range: -0.0828

Max Act: 0.0724. Min Act: -0.0002

Data Index: 805852 (C4 (Web Text))

Max Activating Token Index: 1009

Text #15

Max Range: 0.0828. Min Range: -0.0828

Max Act: 0.0728. Min Act: -0.0002

Data Index: 562944 (C4 (Web Text))

Max Activating Token Index: 618

Text #16

Max Range: 0.0828. Min Range: -0.0828

Max Act: 0.0692. Min Act: -0.0002

Data Index: 1248147 (C4 (Web Text))

Max Activating Token Index: 788

Text #17

Max Range: 0.0828. Min Range: -0.0828

Max Act: 0.0751. Min Act: -0.0002

Data Index: 546254 (C4 (Web Text))

Max Activating Token Index: 739

Text #18

Max Range: 0.0828. Min Range: -0.0828

Max Act: 0.0690. Min Act: -0.0002

Data Index: 708154 (C4 (Web Text))

Max Activating Token Index: 847

Text #19

Max Range: 0.0828. Min Range: -0.0828

Max Act: 0.0715. Min Act: -0.0002

Data Index: 160069 (C4 (Web Text))

Max Activating Token Index: 259