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

Dataset: The Pile

Neuron 3756 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9086. Min Range: -0.9086

Max Act: 0.9086. Min Act: -0.0000

Data Index: 557531 (The Pile)

Max Activating Token Index: 621

Text #1

Max Range: 0.9086. Min Range: -0.9086

Max Act: 0.8088. Min Act: 0.0000

Data Index: 1517711 (The Pile)

Max Activating Token Index: 394

Text #2

Max Range: 0.9086. Min Range: -0.9086

Max Act: 0.8361. Min Act: -0.0000

Data Index: 579886 (The Pile)

Max Activating Token Index: 391

Text #3

Max Range: 0.9086. Min Range: -0.9086

Max Act: 0.7842. Min Act: -0.0000

Data Index: 1729120 (The Pile)

Max Activating Token Index: 302

Text #4

Max Range: 0.9086. Min Range: -0.9086

Max Act: 0.7900. Min Act: -0.0000

Data Index: 716384 (The Pile)

Max Activating Token Index: 217

Text #5

Max Range: 0.9086. Min Range: -0.9086

Max Act: 0.7964. Min Act: 0.0000

Data Index: 715470 (The Pile)

Max Activating Token Index: 53

Text #6

Max Range: 0.9086. Min Range: -0.9086

Max Act: 0.7660. Min Act: -0.0000

Data Index: 639902 (The Pile)

Max Activating Token Index: 442

Text #7

Max Range: 0.9086. Min Range: -0.9086

Max Act: 0.7210. Min Act: -0.0000

Data Index: 1750874 (The Pile)

Max Activating Token Index: 635

Text #8

Max Range: 0.9086. Min Range: -0.9086

Max Act: 0.7519. Min Act: -0.0000

Data Index: 1713252 (The Pile)

Max Activating Token Index: 21

Text #9

Max Range: 0.9086. Min Range: -0.9086

Max Act: 0.7687. Min Act: -0.0000

Data Index: 1900323 (The Pile)

Max Activating Token Index: 904

Text #10

Max Range: 0.9086. Min Range: -0.9086

Max Act: 0.7529. Min Act: -0.0000

Data Index: 824878 (The Pile)

Max Activating Token Index: 409

Text #11

Max Range: 0.9086. Min Range: -0.9086

Max Act: 0.7377. Min Act: 0.0000

Data Index: 1118203 (The Pile)

Max Activating Token Index: 243

Text #12

Max Range: 0.9086. Min Range: -0.9086

Max Act: 0.7410. Min Act: -0.0000

Data Index: 823924 (The Pile)

Max Activating Token Index: 395

Text #13

Max Range: 0.9086. Min Range: -0.9086

Max Act: 0.7361. Min Act: -0.0000

Data Index: 447815 (The Pile)

Max Activating Token Index: 806

Text #14

Max Range: 0.9086. Min Range: -0.9086

Max Act: 0.7530. Min Act: 0.0000

Data Index: 1812065 (The Pile)

Max Activating Token Index: 52

Text #15

Max Range: 0.9086. Min Range: -0.9086

Max Act: 0.6826. Min Act: -0.0000

Data Index: 401192 (The Pile)

Max Activating Token Index: 848

Text #16

Max Range: 0.9086. Min Range: -0.9086

Max Act: 0.7151. Min Act: -0.0000

Data Index: 512681 (The Pile)

Max Activating Token Index: 304

Text #17

Max Range: 0.9086. Min Range: -0.9086

Max Act: 0.7040. Min Act: -0.0000

Data Index: 1568123 (The Pile)

Max Activating Token Index: 161

Text #18

Max Range: 0.9086. Min Range: -0.9086

Max Act: 0.6122. Min Act: -0.0000

Data Index: 1732642 (The Pile)

Max Activating Token Index: 789

Text #19

Max Range: 0.9086. Min Range: -0.9086

Max Act: 0.7673. Min Act: -0.0000

Data Index: 267894 (The Pile)

Max Activating Token Index: 200