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

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

Neuron 1192 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0920. Min Act: -0.0005

Data Index: 281422 (C4 (Web Text))

Max Activating Token Index: 343

Text #1

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0950. Min Act: -0.0005

Data Index: 442127 (C4 (Web Text))

Max Activating Token Index: 732

Text #2

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0881. Min Act: -0.0005

Data Index: 387481 (C4 (Web Text))

Max Activating Token Index: 689

Text #3

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0757. Min Act: -0.0005

Data Index: 792474 (C4 (Web Text))

Max Activating Token Index: 742

Text #4

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0738. Min Act: -0.0005

Data Index: 6824 (C4 (Web Text))

Max Activating Token Index: 584

Text #5

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0745. Min Act: -0.0005

Data Index: 1077037 (C4 (Web Text))

Max Activating Token Index: 323

Text #6

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0710. Min Act: -0.0005

Data Index: 678369 (C4 (Web Text))

Max Activating Token Index: 398

Text #7

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0734. Min Act: -0.0005

Data Index: 845160 (C4 (Web Text))

Max Activating Token Index: 519

Text #8

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0762. Min Act: -0.0005

Data Index: 173113 (C4 (Web Text))

Max Activating Token Index: 410

Text #9

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0751. Min Act: -0.0005

Data Index: 927468 (C4 (Web Text))

Max Activating Token Index: 194

Text #10

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0690. Min Act: -0.0005

Data Index: 794265 (C4 (Web Text))

Max Activating Token Index: 429

Text #11

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0715. Min Act: -0.0005

Data Index: 51257 (C4 (Web Text))

Max Activating Token Index: 354

Text #12

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0748. Min Act: -0.0005

Data Index: 112798 (C4 (Web Text))

Max Activating Token Index: 294

Text #13

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0682. Min Act: -0.0005

Data Index: 85635 (C4 (Web Text))

Max Activating Token Index: 697

Text #14

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0684. Min Act: -0.0005

Data Index: 699141 (C4 (Web Text))

Max Activating Token Index: 578

Text #15

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0707. Min Act: -0.0005

Data Index: 668339 (C4 (Web Text))

Max Activating Token Index: 110

Text #16

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0728. Min Act: -0.0005

Data Index: 630915 (C4 (Web Text))

Max Activating Token Index: 474

Text #17

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0727. Min Act: -0.0005

Data Index: 1283883 (C4 (Web Text))

Max Activating Token Index: 783

Text #18

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0715. Min Act: -0.0005

Data Index: 486085 (C4 (Web Text))

Max Activating Token Index: 376

Text #19

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0684. Min Act: -0.0005

Data Index: 914358 (C4 (Web Text))

Max Activating Token Index: 564