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

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

Neuron 1229 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: 0.0869. Min Range: -0.0869

Max Act: 0.0867. Min Act: -0.0003

Data Index: 140872 (C4 (Web Text))

Max Activating Token Index: 159

Text #1

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0858. Min Act: -0.0003

Data Index: 1276585 (C4 (Web Text))

Max Activating Token Index: 301

Text #2

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0860. Min Act: -0.0003

Data Index: 499190 (C4 (Web Text))

Max Activating Token Index: 57

Text #3

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0869. Min Act: -0.0003

Data Index: 5488 (C4 (Web Text))

Max Activating Token Index: 111

Text #4

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0827. Min Act: -0.0003

Data Index: 237597 (C4 (Web Text))

Max Activating Token Index: 113

Text #5

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0812. Min Act: -0.0003

Data Index: 226255 (C4 (Web Text))

Max Activating Token Index: 114

Text #6

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0768. Min Act: -0.0003

Data Index: 112716 (C4 (Web Text))

Max Activating Token Index: 249

Text #7

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0760. Min Act: -0.0003

Data Index: 965885 (C4 (Web Text))

Max Activating Token Index: 358

Text #8

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0781. Min Act: -0.0002

Data Index: 92128 (C4 (Web Text))

Max Activating Token Index: 237

Text #9

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0804. Min Act: -0.0003

Data Index: 535529 (C4 (Web Text))

Max Activating Token Index: 456

Text #10

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0762. Min Act: -0.0003

Data Index: 1132898 (C4 (Web Text))

Max Activating Token Index: 894

Text #11

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0784. Min Act: -0.0002

Data Index: 54416 (C4 (Web Text))

Max Activating Token Index: 447

Text #12

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0745. Min Act: -0.0003

Data Index: 439665 (C4 (Web Text))

Max Activating Token Index: 565

Text #13

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0770. Min Act: -0.0003

Data Index: 949724 (C4 (Web Text))

Max Activating Token Index: 374

Text #14

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0777. Min Act: -0.0003

Data Index: 678518 (C4 (Web Text))

Max Activating Token Index: 524

Text #15

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0748. Min Act: -0.0004

Data Index: 493895 (C4 (Web Text))

Max Activating Token Index: 463

Text #16

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0734. Min Act: -0.0003

Data Index: 920659 (C4 (Web Text))

Max Activating Token Index: 934

Text #17

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0742. Min Act: -0.0003

Data Index: 909720 (C4 (Web Text))

Max Activating Token Index: 44

Text #18

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0751. Min Act: -0.0003

Data Index: 452179 (C4 (Web Text))

Max Activating Token Index: 618

Text #19

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0747. Min Act: -0.0003

Data Index: 1325481 (C4 (Web Text))

Max Activating Token Index: 453