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

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

Neuron 3922 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0904. Min Act: -0.0000

Data Index: 1017426 (C4 (Web Text))

Max Activating Token Index: 540

Text #1

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0774. Min Act: -0.0000

Data Index: 1316665 (C4 (Web Text))

Max Activating Token Index: 178

Text #2

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0812. Min Act: -0.0000

Data Index: 1022018 (C4 (Web Text))

Max Activating Token Index: 762

Text #3

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0691. Min Act: -0.0000

Data Index: 791270 (C4 (Web Text))

Max Activating Token Index: 182

Text #4

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0770. Min Act: -0.0000

Data Index: 742901 (C4 (Web Text))

Max Activating Token Index: 720

Text #5

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0801. Min Act: -0.0000

Data Index: 358530 (C4 (Web Text))

Max Activating Token Index: 824

Text #6

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0728. Min Act: -0.0000

Data Index: 209771 (C4 (Web Text))

Max Activating Token Index: 752

Text #7

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0746. Min Act: -0.0000

Data Index: 1336748 (C4 (Web Text))

Max Activating Token Index: 561

Text #8

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0736. Min Act: -0.0000

Data Index: 40779 (C4 (Web Text))

Max Activating Token Index: 139

Text #9

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0703. Min Act: -0.0000

Data Index: 613837 (C4 (Web Text))

Max Activating Token Index: 914

Text #10

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0665. Min Act: -0.0000

Data Index: 579778 (C4 (Web Text))

Max Activating Token Index: 549

Text #11

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0695. Min Act: -0.0000

Data Index: 1295233 (C4 (Web Text))

Max Activating Token Index: 1003

Text #12

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0740. Min Act: -0.0000

Data Index: 1036595 (C4 (Web Text))

Max Activating Token Index: 61

Text #13

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0719. Min Act: -0.0000

Data Index: 212991 (C4 (Web Text))

Max Activating Token Index: 990

Text #14

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0734. Min Act: -0.0000

Data Index: 1350620 (C4 (Web Text))

Max Activating Token Index: 713

Text #15

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0680. Min Act: -0.0000

Data Index: 619977 (C4 (Web Text))

Max Activating Token Index: 126

Text #16

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0675. Min Act: -0.0000

Data Index: 550061 (C4 (Web Text))

Max Activating Token Index: 55

Text #17

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0748. Min Act: -0.0000

Data Index: 234737 (C4 (Web Text))

Max Activating Token Index: 479

Text #18

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0741. Min Act: -0.0000

Data Index: 522462 (C4 (Web Text))

Max Activating Token Index: 549

Text #19

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0711. Min Act: -0.0000

Data Index: 210683 (C4 (Web Text))

Max Activating Token Index: 317