Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2940 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.4727. Min Range: -1.4727

Max Act: 1.3150. Min Act: -0.0000

Data Index: 1733810 (The Pile)

Max Activating Token Index: 382

Text #1

Max Range: 1.4727. Min Range: -1.4727

Max Act: 1.3182. Min Act: -0.0000

Data Index: 853966 (The Pile)

Max Activating Token Index: 787

Text #2

Max Range: 1.4727. Min Range: -1.4727

Max Act: 1.4727. Min Act: -0.0000

Data Index: 16495 (The Pile)

Max Activating Token Index: 882

Text #3

Max Range: 1.4727. Min Range: -1.4727

Max Act: 1.2771. Min Act: -0.0000

Data Index: 1961590 (The Pile)

Max Activating Token Index: 452

Text #4

Max Range: 1.4727. Min Range: -1.4727

Max Act: 1.2168. Min Act: -0.0000

Data Index: 548576 (The Pile)

Max Activating Token Index: 539

Text #5

Max Range: 1.4727. Min Range: -1.4727

Max Act: 1.1550. Min Act: -0.0000

Data Index: 300926 (The Pile)

Max Activating Token Index: 828

Text #6

Max Range: 1.4727. Min Range: -1.4727

Max Act: 1.1450. Min Act: -0.0000

Data Index: 822517 (The Pile)

Max Activating Token Index: 825

Text #7

Max Range: 1.4727. Min Range: -1.4727

Max Act: 1.0638. Min Act: -0.0000

Data Index: 490351 (The Pile)

Max Activating Token Index: 972

Text #8

Max Range: 1.4727. Min Range: -1.4727

Max Act: 1.0575. Min Act: -0.0000

Data Index: 752838 (The Pile)

Max Activating Token Index: 766

Text #9

Max Range: 1.4727. Min Range: -1.4727

Max Act: 1.0508. Min Act: -0.0000

Data Index: 1489815 (The Pile)

Max Activating Token Index: 793

Text #10

Max Range: 1.4727. Min Range: -1.4727

Max Act: 0.9999. Min Act: -0.0000

Data Index: 1929981 (The Pile)

Max Activating Token Index: 209

Text #11

Max Range: 1.4727. Min Range: -1.4727

Max Act: 0.9695. Min Act: -0.0000

Data Index: 1423604 (The Pile)

Max Activating Token Index: 553

Text #12

Max Range: 1.4727. Min Range: -1.4727

Max Act: 0.9024. Min Act: -0.0000

Data Index: 660923 (The Pile)

Max Activating Token Index: 910

Text #13

Max Range: 1.4727. Min Range: -1.4727

Max Act: 0.9383. Min Act: -0.0000

Data Index: 821443 (The Pile)

Max Activating Token Index: 627

Text #14

Max Range: 1.4727. Min Range: -1.4727

Max Act: 0.9906. Min Act: -0.0000

Data Index: 988104 (The Pile)

Max Activating Token Index: 830

Text #15

Max Range: 1.4727. Min Range: -1.4727

Max Act: 0.8422. Min Act: -0.0000

Data Index: 775551 (The Pile)

Max Activating Token Index: 965

Text #16

Max Range: 1.4727. Min Range: -1.4727

Max Act: 0.8714. Min Act: -0.0000

Data Index: 358631 (The Pile)

Max Activating Token Index: 641

Text #17

Max Range: 1.4727. Min Range: -1.4727

Max Act: 0.8423. Min Act: -0.0000

Data Index: 1851923 (The Pile)

Max Activating Token Index: 995

Text #18

Max Range: 1.4727. Min Range: -1.4727

Max Act: 0.9148. Min Act: -0.0000

Data Index: 651072 (The Pile)

Max Activating Token Index: 427

Text #19

Max Range: 1.4727. Min Range: -1.4727

Max Act: 0.8882. Min Act: -0.0000

Data Index: 957281 (The Pile)

Max Activating Token Index: 976