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

Dataset: The Pile

Neuron 3766 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: 0.4903. Min Range: -0.4903

Max Act: 0.4713. Min Act: -0.0000

Data Index: 1214046 (The Pile)

Max Activating Token Index: 1002

Text #1

Max Range: 0.4903. Min Range: -0.4903

Max Act: 0.4610. Min Act: -0.0000

Data Index: 930209 (The Pile)

Max Activating Token Index: 371

Text #2

Max Range: 0.4903. Min Range: -0.4903

Max Act: 0.4903. Min Act: -0.0000

Data Index: 1197757 (The Pile)

Max Activating Token Index: 956

Text #3

Max Range: 0.4903. Min Range: -0.4903

Max Act: 0.4598. Min Act: -0.0000

Data Index: 769456 (The Pile)

Max Activating Token Index: 932

Text #4

Max Range: 0.4903. Min Range: -0.4903

Max Act: 0.4720. Min Act: -0.0000

Data Index: 1683107 (The Pile)

Max Activating Token Index: 624

Text #5

Max Range: 0.4903. Min Range: -0.4903

Max Act: 0.4354. Min Act: -0.0000

Data Index: 672159 (The Pile)

Max Activating Token Index: 772

Text #6

Max Range: 0.4903. Min Range: -0.4903

Max Act: 0.4394. Min Act: -0.0000

Data Index: 1146228 (The Pile)

Max Activating Token Index: 60

Text #7

Max Range: 0.4903. Min Range: -0.4903

Max Act: 0.4214. Min Act: -0.0000

Data Index: 1894140 (The Pile)

Max Activating Token Index: 838

Text #8

Max Range: 0.4903. Min Range: -0.4903

Max Act: 0.4399. Min Act: -0.0000

Data Index: 664850 (The Pile)

Max Activating Token Index: 648

Text #9

Max Range: 0.4903. Min Range: -0.4903

Max Act: 0.4407. Min Act: -0.0000

Data Index: 990390 (The Pile)

Max Activating Token Index: 40

Text #10

Max Range: 0.4903. Min Range: -0.4903

Max Act: 0.4318. Min Act: -0.0000

Data Index: 1699791 (The Pile)

Max Activating Token Index: 272

Text #11

Max Range: 0.4903. Min Range: -0.4903

Max Act: 0.4281. Min Act: -0.0000

Data Index: 1296886 (The Pile)

Max Activating Token Index: 32

Text #12

Max Range: 0.4903. Min Range: -0.4903

Max Act: 0.4145. Min Act: -0.0000

Data Index: 1750609 (The Pile)

Max Activating Token Index: 387

Text #13

Max Range: 0.4903. Min Range: -0.4903

Max Act: 0.4162. Min Act: -0.0000

Data Index: 199500 (The Pile)

Max Activating Token Index: 924

Text #14

Max Range: 0.4903. Min Range: -0.4903

Max Act: 0.4357. Min Act: -0.0000

Data Index: 467752 (The Pile)

Max Activating Token Index: 194

Text #15

Max Range: 0.4903. Min Range: -0.4903

Max Act: 0.4260. Min Act: -0.0000

Data Index: 1943022 (The Pile)

Max Activating Token Index: 789

Text #16

Max Range: 0.4903. Min Range: -0.4903

Max Act: 0.4210. Min Act: -0.0000

Data Index: 974902 (The Pile)

Max Activating Token Index: 350

Text #17

Max Range: 0.4903. Min Range: -0.4903

Max Act: 0.4375. Min Act: -0.0000

Data Index: 1082519 (The Pile)

Max Activating Token Index: 772

Text #18

Max Range: 0.4903. Min Range: -0.4903

Max Act: 0.4057. Min Act: -0.0000

Data Index: 1042492 (The Pile)

Max Activating Token Index: 889

Text #19

Max Range: 0.4903. Min Range: -0.4903

Max Act: 0.4269. Min Act: -0.0000

Data Index: 191471 (The Pile)

Max Activating Token Index: 137