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

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

Neuron 4483 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4948. Min Range: -0.4948

Max Act: 0.4948. Min Act: -0.0001

Data Index: 452605 (C4 (Web Text))

Max Activating Token Index: 345

Text #1

Max Range: 0.4948. Min Range: -0.4948

Max Act: 0.4398. Min Act: -0.0001

Data Index: 343895 (C4 (Web Text))

Max Activating Token Index: 620

Text #2

Max Range: 0.4948. Min Range: -0.4948

Max Act: 0.4243. Min Act: -0.0001

Data Index: 1148044 (C4 (Web Text))

Max Activating Token Index: 347

Text #3

Max Range: 0.4948. Min Range: -0.4948

Max Act: 0.4187. Min Act: -0.0001

Data Index: 112241 (C4 (Web Text))

Max Activating Token Index: 531

Text #4

Max Range: 0.4948. Min Range: -0.4948

Max Act: 0.4187. Min Act: -0.0001

Data Index: 1148703 (C4 (Web Text))

Max Activating Token Index: 321

Text #5

Max Range: 0.4948. Min Range: -0.4948

Max Act: 0.3723. Min Act: -0.0001

Data Index: 207316 (C4 (Web Text))

Max Activating Token Index: 627

Text #6

Max Range: 0.4948. Min Range: -0.4948

Max Act: 0.3895. Min Act: -0.0001

Data Index: 926554 (C4 (Web Text))

Max Activating Token Index: 893

Text #7

Max Range: 0.4948. Min Range: -0.4948

Max Act: 0.3856. Min Act: -0.0001

Data Index: 1016722 (C4 (Web Text))

Max Activating Token Index: 575

Text #8

Max Range: 0.4948. Min Range: -0.4948

Max Act: 0.3767. Min Act: -0.0001

Data Index: 1206452 (C4 (Web Text))

Max Activating Token Index: 422

Text #9

Max Range: 0.4948. Min Range: -0.4948

Max Act: 0.3620. Min Act: -0.0001

Data Index: 1077301 (C4 (Web Text))

Max Activating Token Index: 509

Text #10

Max Range: 0.4948. Min Range: -0.4948

Max Act: 0.3706. Min Act: -0.0001

Data Index: 1278914 (C4 (Web Text))

Max Activating Token Index: 956

Text #11

Max Range: 0.4948. Min Range: -0.4948

Max Act: 0.3685. Min Act: -0.0001

Data Index: 1131866 (C4 (Web Text))

Max Activating Token Index: 439

Text #12

Max Range: 0.4948. Min Range: -0.4948

Max Act: 0.3673. Min Act: -0.0001

Data Index: 710307 (C4 (Web Text))

Max Activating Token Index: 996

Text #13

Max Range: 0.4948. Min Range: -0.4948

Max Act: 0.3703. Min Act: -0.0001

Data Index: 120597 (C4 (Web Text))

Max Activating Token Index: 552

Text #14

Max Range: 0.4948. Min Range: -0.4948

Max Act: 0.3549. Min Act: -0.0001

Data Index: 958926 (C4 (Web Text))

Max Activating Token Index: 648

Text #15

Max Range: 0.4948. Min Range: -0.4948

Max Act: 0.3559. Min Act: -0.0001

Data Index: 98761 (C4 (Web Text))

Max Activating Token Index: 980

Text #16

Max Range: 0.4948. Min Range: -0.4948

Max Act: 0.3808. Min Act: -0.0001

Data Index: 769885 (C4 (Web Text))

Max Activating Token Index: 494

Text #17

Max Range: 0.4948. Min Range: -0.4948

Max Act: 0.3500. Min Act: -0.0001

Data Index: 425569 (C4 (Web Text))

Max Activating Token Index: 602

Text #18

Max Range: 0.4948. Min Range: -0.4948

Max Act: 0.3501. Min Act: -0.0001

Data Index: 116605 (C4 (Web Text))

Max Activating Token Index: 827

Text #19

Max Range: 0.4948. Min Range: -0.4948

Max Act: 0.3690. Min Act: -0.0001

Data Index: 235896 (C4 (Web Text))

Max Activating Token Index: 297