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

Dataset: The Pile

Neuron 705 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: 1.0258. Min Range: -1.0258

Max Act: 1.0258. Min Act: -0.0000

Data Index: 1032454 (The Pile)

Max Activating Token Index: 647

Text #1

Max Range: 1.0258. Min Range: -1.0258

Max Act: 0.9309. Min Act: -0.0000

Data Index: 586590 (The Pile)

Max Activating Token Index: 580

Text #2

Max Range: 1.0258. Min Range: -1.0258

Max Act: 0.9689. Min Act: -0.0000

Data Index: 1837769 (The Pile)

Max Activating Token Index: 466

Text #3

Max Range: 1.0258. Min Range: -1.0258

Max Act: 0.8794. Min Act: -0.0000

Data Index: 1119066 (The Pile)

Max Activating Token Index: 513

Text #4

Max Range: 1.0258. Min Range: -1.0258

Max Act: 0.8210. Min Act: -0.0000

Data Index: 1753972 (The Pile)

Max Activating Token Index: 800

Text #5

Max Range: 1.0258. Min Range: -1.0258

Max Act: 0.8385. Min Act: -0.0000

Data Index: 1050829 (The Pile)

Max Activating Token Index: 558

Text #6

Max Range: 1.0258. Min Range: -1.0258

Max Act: 0.8274. Min Act: -0.0000

Data Index: 1939836 (The Pile)

Max Activating Token Index: 669

Text #7

Max Range: 1.0258. Min Range: -1.0258

Max Act: 0.8668. Min Act: -0.0000

Data Index: 933364 (The Pile)

Max Activating Token Index: 645

Text #8

Max Range: 1.0258. Min Range: -1.0258

Max Act: 0.7985. Min Act: -0.0000

Data Index: 850484 (The Pile)

Max Activating Token Index: 394

Text #9

Max Range: 1.0258. Min Range: -1.0258

Max Act: 0.8465. Min Act: -0.0000

Data Index: 953880 (The Pile)

Max Activating Token Index: 241

Text #10

Max Range: 1.0258. Min Range: -1.0258

Max Act: 0.7862. Min Act: -0.0000

Data Index: 1001664 (The Pile)

Max Activating Token Index: 370

Text #11

Max Range: 1.0258. Min Range: -1.0258

Max Act: 0.7433. Min Act: -0.0000

Data Index: 261931 (The Pile)

Max Activating Token Index: 736

Text #12

Max Range: 1.0258. Min Range: -1.0258

Max Act: 0.7923. Min Act: -0.0000

Data Index: 997284 (The Pile)

Max Activating Token Index: 707

Text #13

Max Range: 1.0258. Min Range: -1.0258

Max Act: 0.8109. Min Act: -0.0000

Data Index: 1438280 (The Pile)

Max Activating Token Index: 764

Text #14

Max Range: 1.0258. Min Range: -1.0258

Max Act: 0.8077. Min Act: -0.0000

Data Index: 963549 (The Pile)

Max Activating Token Index: 237

Text #15

Max Range: 1.0258. Min Range: -1.0258

Max Act: 0.7737. Min Act: -0.0000

Data Index: 1799864 (The Pile)

Max Activating Token Index: 177

Text #16

Max Range: 1.0258. Min Range: -1.0258

Max Act: 0.7732. Min Act: -0.0000

Data Index: 408531 (The Pile)

Max Activating Token Index: 359

Text #17

Max Range: 1.0258. Min Range: -1.0258

Max Act: 0.8212. Min Act: -0.0000

Data Index: 1129930 (The Pile)

Max Activating Token Index: 693

Text #18

Max Range: 1.0258. Min Range: -1.0258

Max Act: 0.7179. Min Act: -0.0000

Data Index: 1600076 (The Pile)

Max Activating Token Index: 499

Text #19

Max Range: 1.0258. Min Range: -1.0258

Max Act: 0.7019. Min Act: -0.0000

Data Index: 796847 (The Pile)

Max Activating Token Index: 909