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

Dataset: The Pile

Neuron 432 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: 1.9761. Min Range: -1.9761

Max Act: 1.9761. Min Act: -0.0000

Data Index: 1545783 (The Pile)

Max Activating Token Index: 364

Text #1

Max Range: 1.9761. Min Range: -1.9761

Max Act: 1.8984. Min Act: -0.0000

Data Index: 1144545 (The Pile)

Max Activating Token Index: 413

Text #2

Max Range: 1.9761. Min Range: -1.9761

Max Act: 1.8695. Min Act: -0.0000

Data Index: 1611190 (The Pile)

Max Activating Token Index: 270

Text #3

Max Range: 1.9761. Min Range: -1.9761

Max Act: 1.8617. Min Act: -0.0000

Data Index: 537272 (The Pile)

Max Activating Token Index: 626

Text #4

Max Range: 1.9761. Min Range: -1.9761

Max Act: 1.8411. Min Act: -0.0000

Data Index: 938346 (The Pile)

Max Activating Token Index: 334

Text #5

Max Range: 1.9761. Min Range: -1.9761

Max Act: 1.8275. Min Act: -0.0000

Data Index: 1653894 (The Pile)

Max Activating Token Index: 588

Text #6

Max Range: 1.9761. Min Range: -1.9761

Max Act: 1.8038. Min Act: -0.0000

Data Index: 1765846 (The Pile)

Max Activating Token Index: 926

Text #7

Max Range: 1.9761. Min Range: -1.9761

Max Act: 1.7971. Min Act: -0.0000

Data Index: 1389529 (The Pile)

Max Activating Token Index: 603

Text #8

Max Range: 1.9761. Min Range: -1.9761

Max Act: 1.6833. Min Act: -0.0000

Data Index: 383695 (The Pile)

Max Activating Token Index: 586

Text #9

Max Range: 1.9761. Min Range: -1.9761

Max Act: 1.6577. Min Act: -0.0000

Data Index: 1785286 (The Pile)

Max Activating Token Index: 169

Text #10

Max Range: 1.9761. Min Range: -1.9761

Max Act: 1.7295. Min Act: -0.0000

Data Index: 761395 (The Pile)

Max Activating Token Index: 305

Text #11

Max Range: 1.9761. Min Range: -1.9761

Max Act: 1.6171. Min Act: -0.0000

Data Index: 235777 (The Pile)

Max Activating Token Index: 864

Text #12

Max Range: 1.9761. Min Range: -1.9761

Max Act: 1.7012. Min Act: -0.0000

Data Index: 1990535 (The Pile)

Max Activating Token Index: 440

Text #13

Max Range: 1.9761. Min Range: -1.9761

Max Act: 1.7012. Min Act: -0.0000

Data Index: 1179373 (The Pile)

Max Activating Token Index: 687

Text #14

Max Range: 1.9761. Min Range: -1.9761

Max Act: 1.7220. Min Act: -0.0000

Data Index: 1428040 (The Pile)

Max Activating Token Index: 35

Text #15

Max Range: 1.9761. Min Range: -1.9761

Max Act: 1.7172. Min Act: -0.0000

Data Index: 447336 (The Pile)

Max Activating Token Index: 429

Text #16

Max Range: 1.9761. Min Range: -1.9761

Max Act: 1.6183. Min Act: -0.0000

Data Index: 1865959 (The Pile)

Max Activating Token Index: 488

Text #17

Max Range: 1.9761. Min Range: -1.9761

Max Act: 1.6791. Min Act: -0.0000

Data Index: 1744229 (The Pile)

Max Activating Token Index: 387

Text #18

Max Range: 1.9761. Min Range: -1.9761

Max Act: 1.6856. Min Act: -0.0000

Data Index: 1718941 (The Pile)

Max Activating Token Index: 463

Text #19

Max Range: 1.9761. Min Range: -1.9761

Max Act: 1.8874. Min Act: -0.0000

Data Index: 1157830 (The Pile)

Max Activating Token Index: 879