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

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

Neuron 1235 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: 0.1151. Min Range: -0.1151

Max Act: 0.1151. Min Act: -0.0003

Data Index: 248021 (C4 (Web Text))

Max Activating Token Index: 506

Text #1

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.1010. Min Act: -0.0003

Data Index: 695074 (C4 (Web Text))

Max Activating Token Index: 360

Text #2

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.0908. Min Act: -0.0003

Data Index: 784918 (C4 (Web Text))

Max Activating Token Index: 938

Text #3

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.0912. Min Act: -0.0003

Data Index: 577621 (C4 (Web Text))

Max Activating Token Index: 791

Text #4

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.0857. Min Act: -0.0004

Data Index: 1140445 (C4 (Web Text))

Max Activating Token Index: 961

Text #5

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.0857. Min Act: -0.0003

Data Index: 113072 (C4 (Web Text))

Max Activating Token Index: 848

Text #6

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.0813. Min Act: -0.0004

Data Index: 792264 (C4 (Web Text))

Max Activating Token Index: 600

Text #7

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.0806. Min Act: -0.0003

Data Index: 1003975 (C4 (Web Text))

Max Activating Token Index: 342

Text #8

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.0851. Min Act: -0.0003

Data Index: 129189 (C4 (Web Text))

Max Activating Token Index: 488

Text #9

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.0801. Min Act: -0.0003

Data Index: 1021411 (C4 (Web Text))

Max Activating Token Index: 661

Text #10

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.0773. Min Act: -0.0003

Data Index: 716027 (C4 (Web Text))

Max Activating Token Index: 764

Text #11

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.0753. Min Act: -0.0004

Data Index: 830634 (C4 (Web Text))

Max Activating Token Index: 522

Text #12

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.0788. Min Act: -0.0003

Data Index: 840501 (C4 (Web Text))

Max Activating Token Index: 677

Text #13

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.0791. Min Act: -0.0003

Data Index: 813998 (C4 (Web Text))

Max Activating Token Index: 252

Text #14

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.0730. Min Act: -0.0003

Data Index: 102375 (C4 (Web Text))

Max Activating Token Index: 506

Text #15

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.0768. Min Act: -0.0003

Data Index: 755782 (C4 (Web Text))

Max Activating Token Index: 328

Text #16

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.0774. Min Act: -0.0003

Data Index: 879166 (C4 (Web Text))

Max Activating Token Index: 833

Text #17

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.0759. Min Act: -0.0003

Data Index: 530923 (C4 (Web Text))

Max Activating Token Index: 809

Text #18

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.0742. Min Act: -0.0003

Data Index: 543200 (C4 (Web Text))

Max Activating Token Index: 905

Text #19

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.0783. Min Act: -0.0003

Data Index: 1226692 (C4 (Web Text))

Max Activating Token Index: 870