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

Dataset: The Pile

Neuron 2366 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.5807. Min Range: -5.5807

Max Act: 5.5807. Min Act: -0.0000

Data Index: 1812878 (The Pile)

Max Activating Token Index: 252

Text #1

Max Range: 5.5807. Min Range: -5.5807

Max Act: 5.3840. Min Act: -0.0000

Data Index: 103634 (The Pile)

Max Activating Token Index: 165

Text #2

Max Range: 5.5807. Min Range: -5.5807

Max Act: 5.2301. Min Act: -0.0000

Data Index: 352304 (The Pile)

Max Activating Token Index: 131

Text #3

Max Range: 5.5807. Min Range: -5.5807

Max Act: 5.2321. Min Act: -0.0000

Data Index: 1795030 (The Pile)

Max Activating Token Index: 145

Text #4

Max Range: 5.5807. Min Range: -5.5807

Max Act: 5.4128. Min Act: -0.0000

Data Index: 1034478 (The Pile)

Max Activating Token Index: 443

Text #5

Max Range: 5.5807. Min Range: -5.5807

Max Act: 5.0327. Min Act: -0.0000

Data Index: 198944 (The Pile)

Max Activating Token Index: 210

Text #6

Max Range: 5.5807. Min Range: -5.5807

Max Act: 5.2930. Min Act: -0.0000

Data Index: 1495667 (The Pile)

Max Activating Token Index: 30

Text #7

Max Range: 5.5807. Min Range: -5.5807

Max Act: 5.0189. Min Act: -0.0000

Data Index: 895696 (The Pile)

Max Activating Token Index: 5

Text #8

Max Range: 5.5807. Min Range: -5.5807

Max Act: 4.9649. Min Act: -0.0000

Data Index: 89392 (The Pile)

Max Activating Token Index: 341

Text #9

Max Range: 5.5807. Min Range: -5.5807

Max Act: 4.8812. Min Act: -0.0000

Data Index: 221560 (The Pile)

Max Activating Token Index: 48

Text #10

Max Range: 5.5807. Min Range: -5.5807

Max Act: 4.9028. Min Act: -0.0000

Data Index: 351427 (The Pile)

Max Activating Token Index: 666

Text #11

Max Range: 5.5807. Min Range: -5.5807

Max Act: 4.8984. Min Act: -0.0000

Data Index: 1173029 (The Pile)

Max Activating Token Index: 10

Text #12

Max Range: 5.5807. Min Range: -5.5807

Max Act: 4.7086. Min Act: -0.0000

Data Index: 153550 (The Pile)

Max Activating Token Index: 750

Text #13

Max Range: 5.5807. Min Range: -5.5807

Max Act: 4.8807. Min Act: -0.0000

Data Index: 816292 (The Pile)

Max Activating Token Index: 41

Text #14

Max Range: 5.5807. Min Range: -5.5807

Max Act: 4.6650. Min Act: -0.0000

Data Index: 1977490 (The Pile)

Max Activating Token Index: 109

Text #15

Max Range: 5.5807. Min Range: -5.5807

Max Act: 4.8363. Min Act: -0.0000

Data Index: 145874 (The Pile)

Max Activating Token Index: 992

Text #16

Max Range: 5.5807. Min Range: -5.5807

Max Act: 4.8183. Min Act: -0.0000

Data Index: 1241122 (The Pile)

Max Activating Token Index: 92

Text #17

Max Range: 5.5807. Min Range: -5.5807

Max Act: 4.8028. Min Act: -0.0000

Data Index: 1195785 (The Pile)

Max Activating Token Index: 99

Text #18

Max Range: 5.5807. Min Range: -5.5807

Max Act: 4.7951. Min Act: -0.0000

Data Index: 1220219 (The Pile)

Max Activating Token Index: 775

Text #19

Max Range: 5.5807. Min Range: -5.5807

Max Act: 4.7767. Min Act: -0.0000

Data Index: 597948 (The Pile)

Max Activating Token Index: 548