Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 262 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0719. Min Range: -0.0719

Max Act: 0.0692. Min Act: -0.0003

Data Index: 1315823 (C4 (Web Text))

Max Activating Token Index: 624

Text #1

Max Range: 0.0719. Min Range: -0.0719

Max Act: 0.0719. Min Act: -0.0003

Data Index: 682897 (C4 (Web Text))

Max Activating Token Index: 661

Text #2

Max Range: 0.0719. Min Range: -0.0719

Max Act: 0.0714. Min Act: -0.0003

Data Index: 1235901 (C4 (Web Text))

Max Activating Token Index: 870

Text #3

Max Range: 0.0719. Min Range: -0.0719

Max Act: 0.0669. Min Act: -0.0003

Data Index: 75073 (C4 (Web Text))

Max Activating Token Index: 631

Text #4

Max Range: 0.0719. Min Range: -0.0719

Max Act: 0.0671. Min Act: -0.0003

Data Index: 1199409 (C4 (Web Text))

Max Activating Token Index: 611

Text #5

Max Range: 0.0719. Min Range: -0.0719

Max Act: 0.0601. Min Act: -0.0003

Data Index: 437767 (C4 (Web Text))

Max Activating Token Index: 820

Text #6

Max Range: 0.0719. Min Range: -0.0719

Max Act: 0.0632. Min Act: -0.0003

Data Index: 785255 (C4 (Web Text))

Max Activating Token Index: 778

Text #7

Max Range: 0.0719. Min Range: -0.0719

Max Act: 0.0636. Min Act: -0.0003

Data Index: 592227 (C4 (Web Text))

Max Activating Token Index: 838

Text #8

Max Range: 0.0719. Min Range: -0.0719

Max Act: 0.0640. Min Act: -0.0003

Data Index: 276813 (C4 (Web Text))

Max Activating Token Index: 368

Text #9

Max Range: 0.0719. Min Range: -0.0719

Max Act: 0.0510. Min Act: -0.0003

Data Index: 988102 (C4 (Web Text))

Max Activating Token Index: 613

Text #10

Max Range: 0.0719. Min Range: -0.0719

Max Act: 0.0543. Min Act: -0.0003

Data Index: 1334961 (C4 (Web Text))

Max Activating Token Index: 807

Text #11

Max Range: 0.0719. Min Range: -0.0719

Max Act: 0.0580. Min Act: -0.0003

Data Index: 587853 (C4 (Web Text))

Max Activating Token Index: 963

Text #12

Max Range: 0.0719. Min Range: -0.0719

Max Act: 0.0512. Min Act: -0.0003

Data Index: 59932 (C4 (Web Text))

Max Activating Token Index: 546

Text #13

Max Range: 0.0719. Min Range: -0.0719

Max Act: 0.0612. Min Act: -0.0003

Data Index: 235413 (C4 (Web Text))

Max Activating Token Index: 596

Text #14

Max Range: 0.0719. Min Range: -0.0719

Max Act: 0.0591. Min Act: -0.0003

Data Index: 996713 (C4 (Web Text))

Max Activating Token Index: 301

Text #15

Max Range: 0.0719. Min Range: -0.0719

Max Act: 0.0602. Min Act: -0.0003

Data Index: 149694 (C4 (Web Text))

Max Activating Token Index: 961

Text #16

Max Range: 0.0719. Min Range: -0.0719

Max Act: 0.0584. Min Act: -0.0003

Data Index: 1342995 (C4 (Web Text))

Max Activating Token Index: 701

Text #17

Max Range: 0.0719. Min Range: -0.0719

Max Act: 0.0635. Min Act: -0.0003

Data Index: 1481596 (Python Code)

Max Activating Token Index: 779

Text #18

Max Range: 0.0719. Min Range: -0.0719

Max Act: 0.0603. Min Act: -0.0003

Data Index: 1447853 (Python Code)

Max Activating Token Index: 108

Text #19

Max Range: 0.0719. Min Range: -0.0719

Max Act: 0.0569. Min Act: -0.0003

Data Index: 1634195 (Python Code)

Max Activating Token Index: 869