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

Dataset: The Pile

Neuron 3337 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5062. Min Range: -0.5062

Max Act: 0.5062. Min Act: -0.0000

Data Index: 1847773 (The Pile)

Max Activating Token Index: 218

Text #1

Max Range: 0.5062. Min Range: -0.5062

Max Act: 0.5011. Min Act: -0.0000

Data Index: 283586 (The Pile)

Max Activating Token Index: 510

Text #2

Max Range: 0.5062. Min Range: -0.5062

Max Act: 0.4882. Min Act: 0.0000

Data Index: 1357525 (The Pile)

Max Activating Token Index: 192

Text #3

Max Range: 0.5062. Min Range: -0.5062

Max Act: 0.4420. Min Act: -0.0000

Data Index: 725943 (The Pile)

Max Activating Token Index: 209

Text #4

Max Range: 0.5062. Min Range: -0.5062

Max Act: 0.3882. Min Act: -0.0000

Data Index: 1428986 (The Pile)

Max Activating Token Index: 895

Text #5

Max Range: 0.5062. Min Range: -0.5062

Max Act: 0.3743. Min Act: 0.0000

Data Index: 404272 (The Pile)

Max Activating Token Index: 918

Text #6

Max Range: 0.5062. Min Range: -0.5062

Max Act: 0.3724. Min Act: 0.0000

Data Index: 218806 (The Pile)

Max Activating Token Index: 137

Text #7

Max Range: 0.5062. Min Range: -0.5062

Max Act: 0.3472. Min Act: -0.0000

Data Index: 1298048 (The Pile)

Max Activating Token Index: 30

Text #8

Max Range: 0.5062. Min Range: -0.5062

Max Act: 0.3284. Min Act: -0.0000

Data Index: 84092 (The Pile)

Max Activating Token Index: 242

Text #9

Max Range: 0.5062. Min Range: -0.5062

Max Act: 0.3025. Min Act: -0.0000

Data Index: 1697077 (The Pile)

Max Activating Token Index: 286

Text #10

Max Range: 0.5062. Min Range: -0.5062

Max Act: 0.3263. Min Act: 0.0000

Data Index: 1326170 (The Pile)

Max Activating Token Index: 160

Text #11

Max Range: 0.5062. Min Range: -0.5062

Max Act: 0.3117. Min Act: -0.0000

Data Index: 1008239 (The Pile)

Max Activating Token Index: 904

Text #12

Max Range: 0.5062. Min Range: -0.5062

Max Act: 0.3066. Min Act: -0.0000

Data Index: 807530 (The Pile)

Max Activating Token Index: 282

Text #13

Max Range: 0.5062. Min Range: -0.5062

Max Act: 0.3258. Min Act: -0.0000

Data Index: 225453 (The Pile)

Max Activating Token Index: 907

Text #14

Max Range: 0.5062. Min Range: -0.5062

Max Act: 0.2985. Min Act: -0.0000

Data Index: 42302 (The Pile)

Max Activating Token Index: 689

Text #15

Max Range: 0.5062. Min Range: -0.5062

Max Act: 0.3236. Min Act: -0.0000

Data Index: 1616574 (The Pile)

Max Activating Token Index: 849

Text #16

Max Range: 0.5062. Min Range: -0.5062

Max Act: 0.3136. Min Act: -0.0000

Data Index: 569902 (The Pile)

Max Activating Token Index: 485

Text #17

Max Range: 0.5062. Min Range: -0.5062

Max Act: 0.2737. Min Act: -0.0000

Data Index: 1213817 (The Pile)

Max Activating Token Index: 941

Text #18

Max Range: 0.5062. Min Range: -0.5062

Max Act: 0.2896. Min Act: -0.0000

Data Index: 831183 (The Pile)

Max Activating Token Index: 285

Text #19

Max Range: 0.5062. Min Range: -0.5062

Max Act: 0.2996. Min Act: -0.0000

Data Index: 397965 (The Pile)

Max Activating Token Index: 248