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

Dataset: The Pile

Neuron 3292 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2892. Min Range: -0.2892

Max Act: 0.2776. Min Act: -0.0000

Data Index: 1441735 (The Pile)

Max Activating Token Index: 395

Text #1

Max Range: 0.2892. Min Range: -0.2892

Max Act: 0.2744. Min Act: -0.0000

Data Index: 1646619 (The Pile)

Max Activating Token Index: 330

Text #2

Max Range: 0.2892. Min Range: -0.2892

Max Act: 0.2617. Min Act: -0.0000

Data Index: 229232 (The Pile)

Max Activating Token Index: 160

Text #3

Max Range: 0.2892. Min Range: -0.2892

Max Act: 0.2892. Min Act: -0.0000

Data Index: 1198068 (The Pile)

Max Activating Token Index: 818

Text #4

Max Range: 0.2892. Min Range: -0.2892

Max Act: 0.2486. Min Act: -0.0000

Data Index: 1068270 (The Pile)

Max Activating Token Index: 684

Text #5

Max Range: 0.2892. Min Range: -0.2892

Max Act: 0.2347. Min Act: -0.0000

Data Index: 1747229 (The Pile)

Max Activating Token Index: 880

Text #6

Max Range: 0.2892. Min Range: -0.2892

Max Act: 0.2210. Min Act: -0.0000

Data Index: 1248651 (The Pile)

Max Activating Token Index: 634

Text #7

Max Range: 0.2892. Min Range: -0.2892

Max Act: 0.2374. Min Act: -0.0000

Data Index: 551043 (The Pile)

Max Activating Token Index: 449

Text #8

Max Range: 0.2892. Min Range: -0.2892

Max Act: 0.2149. Min Act: -0.0000

Data Index: 686163 (The Pile)

Max Activating Token Index: 138

Text #9

Max Range: 0.2892. Min Range: -0.2892

Max Act: 0.2275. Min Act: -0.0000

Data Index: 181512 (The Pile)

Max Activating Token Index: 119

Text #10

Max Range: 0.2892. Min Range: -0.2892

Max Act: 0.2196. Min Act: -0.0000

Data Index: 1642871 (The Pile)

Max Activating Token Index: 711

Text #11

Max Range: 0.2892. Min Range: -0.2892

Max Act: 0.2018. Min Act: -0.0001

Data Index: 1528835 (The Pile)

Max Activating Token Index: 936

Text #12

Max Range: 0.2892. Min Range: -0.2892

Max Act: 0.1989. Min Act: -0.0000

Data Index: 214206 (The Pile)

Max Activating Token Index: 169

Text #13

Max Range: 0.2892. Min Range: -0.2892

Max Act: 0.2018. Min Act: -0.0000

Data Index: 1665598 (The Pile)

Max Activating Token Index: 693

Text #14

Max Range: 0.2892. Min Range: -0.2892

Max Act: 0.1961. Min Act: -0.0000

Data Index: 930857 (The Pile)

Max Activating Token Index: 390

Text #15

Max Range: 0.2892. Min Range: -0.2892

Max Act: 0.1943. Min Act: -0.0000

Data Index: 1131803 (The Pile)

Max Activating Token Index: 549

Text #16

Max Range: 0.2892. Min Range: -0.2892

Max Act: 0.2016. Min Act: -0.0001

Data Index: 1614864 (The Pile)

Max Activating Token Index: 988

Text #17

Max Range: 0.2892. Min Range: -0.2892

Max Act: 0.1994. Min Act: -0.0000

Data Index: 1133779 (The Pile)

Max Activating Token Index: 387

Text #18

Max Range: 0.2892. Min Range: -0.2892

Max Act: 0.2036. Min Act: -0.0000

Data Index: 169501 (The Pile)

Max Activating Token Index: 864

Text #19

Max Range: 0.2892. Min Range: -0.2892

Max Act: 0.2040. Min Act: -0.0000

Data Index: 93246 (The Pile)

Max Activating Token Index: 241