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

Dataset: The Pile

Neuron 3500 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3801. Min Range: -0.3801

Max Act: 0.3801. Min Act: -0.0000

Data Index: 203932 (The Pile)

Max Activating Token Index: 734

Text #1

Max Range: 0.3801. Min Range: -0.3801

Max Act: 0.3279. Min Act: -0.0000

Data Index: 575090 (The Pile)

Max Activating Token Index: 898

Text #2

Max Range: 0.3801. Min Range: -0.3801

Max Act: 0.3529. Min Act: -0.0000

Data Index: 1626673 (The Pile)

Max Activating Token Index: 735

Text #3

Max Range: 0.3801. Min Range: -0.3801

Max Act: 0.2957. Min Act: -0.0000

Data Index: 464726 (The Pile)

Max Activating Token Index: 544

Text #4

Max Range: 0.3801. Min Range: -0.3801

Max Act: 0.3146. Min Act: -0.0000

Data Index: 620782 (The Pile)

Max Activating Token Index: 123

Text #5

Max Range: 0.3801. Min Range: -0.3801

Max Act: 0.3397. Min Act: -0.0000

Data Index: 1636276 (The Pile)

Max Activating Token Index: 891

Text #6

Max Range: 0.3801. Min Range: -0.3801

Max Act: 0.2702. Min Act: -0.0000

Data Index: 1106451 (The Pile)

Max Activating Token Index: 860

Text #7

Max Range: 0.3801. Min Range: -0.3801

Max Act: 0.2991. Min Act: -0.0000

Data Index: 1854182 (The Pile)

Max Activating Token Index: 936

Text #8

Max Range: 0.3801. Min Range: -0.3801

Max Act: 0.2970. Min Act: -0.0000

Data Index: 231665 (The Pile)

Max Activating Token Index: 916

Text #9

Max Range: 0.3801. Min Range: -0.3801

Max Act: 0.2954. Min Act: -0.0000

Data Index: 91777 (The Pile)

Max Activating Token Index: 854

Text #10

Max Range: 0.3801. Min Range: -0.3801

Max Act: 0.3047. Min Act: -0.0000

Data Index: 582111 (The Pile)

Max Activating Token Index: 807

Text #11

Max Range: 0.3801. Min Range: -0.3801

Max Act: 0.3714. Min Act: -0.0000

Data Index: 204516 (The Pile)

Max Activating Token Index: 664

Text #12

Max Range: 0.3801. Min Range: -0.3801

Max Act: 0.2844. Min Act: -0.0000

Data Index: 921067 (The Pile)

Max Activating Token Index: 1016

Text #13

Max Range: 0.3801. Min Range: -0.3801

Max Act: 0.3175. Min Act: -0.0000

Data Index: 1048459 (The Pile)

Max Activating Token Index: 655

Text #14

Max Range: 0.3801. Min Range: -0.3801

Max Act: 0.2883. Min Act: -0.0000

Data Index: 369881 (The Pile)

Max Activating Token Index: 622

Text #15

Max Range: 0.3801. Min Range: -0.3801

Max Act: 0.3149. Min Act: -0.0000

Data Index: 492310 (The Pile)

Max Activating Token Index: 705

Text #16

Max Range: 0.3801. Min Range: -0.3801

Max Act: 0.2888. Min Act: -0.0000

Data Index: 843108 (The Pile)

Max Activating Token Index: 620

Text #17

Max Range: 0.3801. Min Range: -0.3801

Max Act: 0.2967. Min Act: -0.0000

Data Index: 359503 (The Pile)

Max Activating Token Index: 996

Text #18

Max Range: 0.3801. Min Range: -0.3801

Max Act: 0.2673. Min Act: -0.0000

Data Index: 1693397 (The Pile)

Max Activating Token Index: 656

Text #19

Max Range: 0.3801. Min Range: -0.3801

Max Act: 0.3019. Min Act: -0.0000

Data Index: 1184810 (The Pile)

Max Activating Token Index: 818