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

Dataset: The Pile

Neuron 1243 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8248. Min Range: -0.8248

Max Act: 0.8248. Min Act: -0.0000

Data Index: 1580518 (The Pile)

Max Activating Token Index: 282

Text #1

Max Range: 0.8248. Min Range: -0.8248

Max Act: 0.6420. Min Act: -0.0000

Data Index: 883564 (The Pile)

Max Activating Token Index: 621

Text #2

Max Range: 0.8248. Min Range: -0.8248

Max Act: 0.6103. Min Act: -0.0000

Data Index: 983778 (The Pile)

Max Activating Token Index: 787

Text #3

Max Range: 0.8248. Min Range: -0.8248

Max Act: 0.5998. Min Act: -0.0000

Data Index: 1773470 (The Pile)

Max Activating Token Index: 152

Text #4

Max Range: 0.8248. Min Range: -0.8248

Max Act: 0.5571. Min Act: -0.0000

Data Index: 245435 (The Pile)

Max Activating Token Index: 18

Text #5

Max Range: 0.8248. Min Range: -0.8248

Max Act: 0.6033. Min Act: -0.0000

Data Index: 1754 (The Pile)

Max Activating Token Index: 833

Text #6

Max Range: 0.8248. Min Range: -0.8248

Max Act: 0.5643. Min Act: -0.0000

Data Index: 1819499 (The Pile)

Max Activating Token Index: 525

Text #7

Max Range: 0.8248. Min Range: -0.8248

Max Act: 0.5777. Min Act: -0.0000

Data Index: 1438328 (The Pile)

Max Activating Token Index: 217

Text #8

Max Range: 0.8248. Min Range: -0.8248

Max Act: 0.5706. Min Act: -0.0000

Data Index: 1826693 (The Pile)

Max Activating Token Index: 771

Text #9

Max Range: 0.8248. Min Range: -0.8248

Max Act: 0.5483. Min Act: -0.0000

Data Index: 643723 (The Pile)

Max Activating Token Index: 313

Text #10

Max Range: 0.8248. Min Range: -0.8248

Max Act: 0.5649. Min Act: -0.0000

Data Index: 272294 (The Pile)

Max Activating Token Index: 728

Text #11

Max Range: 0.8248. Min Range: -0.8248

Max Act: 0.5280. Min Act: -0.0000

Data Index: 1841684 (The Pile)

Max Activating Token Index: 607

Text #12

Max Range: 0.8248. Min Range: -0.8248

Max Act: 0.5372. Min Act: -0.0000

Data Index: 266797 (The Pile)

Max Activating Token Index: 873

Text #13

Max Range: 0.8248. Min Range: -0.8248

Max Act: 0.5439. Min Act: -0.0000

Data Index: 857883 (The Pile)

Max Activating Token Index: 778

Text #14

Max Range: 0.8248. Min Range: -0.8248

Max Act: 0.5423. Min Act: -0.0000

Data Index: 1514865 (The Pile)

Max Activating Token Index: 354

Text #15

Max Range: 0.8248. Min Range: -0.8248

Max Act: 0.5110. Min Act: -0.0000

Data Index: 1995911 (The Pile)

Max Activating Token Index: 619

Text #16

Max Range: 0.8248. Min Range: -0.8248

Max Act: 0.5082. Min Act: -0.0000

Data Index: 403487 (The Pile)

Max Activating Token Index: 604

Text #17

Max Range: 0.8248. Min Range: -0.8248

Max Act: 0.4871. Min Act: -0.0000

Data Index: 918298 (The Pile)

Max Activating Token Index: 819

Text #18

Max Range: 0.8248. Min Range: -0.8248

Max Act: 0.4678. Min Act: -0.0000

Data Index: 794305 (The Pile)

Max Activating Token Index: 786

Text #19

Max Range: 0.8248. Min Range: -0.8248

Max Act: 0.4771. Min Act: -0.0000

Data Index: 1170716 (The Pile)

Max Activating Token Index: 935