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

Dataset: The Pile

Neuron 3211 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7198. Min Range: -0.7198

Max Act: 0.7198. Min Act: -0.0000

Data Index: 797810 (The Pile)

Max Activating Token Index: 457

Text #1

Max Range: 0.7198. Min Range: -0.7198

Max Act: 0.5859. Min Act: -0.0000

Data Index: 723411 (The Pile)

Max Activating Token Index: 930

Text #2

Max Range: 0.7198. Min Range: -0.7198

Max Act: 0.5819. Min Act: -0.0000

Data Index: 1037825 (The Pile)

Max Activating Token Index: 558

Text #3

Max Range: 0.7198. Min Range: -0.7198

Max Act: 0.6019. Min Act: -0.0000

Data Index: 560808 (The Pile)

Max Activating Token Index: 277

Text #4

Max Range: 0.7198. Min Range: -0.7198

Max Act: 0.5793. Min Act: -0.0000

Data Index: 697940 (The Pile)

Max Activating Token Index: 223

Text #5

Max Range: 0.7198. Min Range: -0.7198

Max Act: 0.5118. Min Act: -0.0000

Data Index: 930090 (The Pile)

Max Activating Token Index: 971

Text #6

Max Range: 0.7198. Min Range: -0.7198

Max Act: 0.5813. Min Act: -0.0000

Data Index: 1765372 (The Pile)

Max Activating Token Index: 40

Text #7

Max Range: 0.7198. Min Range: -0.7198

Max Act: 0.5425. Min Act: -0.0000

Data Index: 1339715 (The Pile)

Max Activating Token Index: 444

Text #8

Max Range: 0.7198. Min Range: -0.7198

Max Act: 0.5957. Min Act: -0.0000

Data Index: 859950 (The Pile)

Max Activating Token Index: 862

Text #9

Max Range: 0.7198. Min Range: -0.7198

Max Act: 0.5074. Min Act: -0.0000

Data Index: 566004 (The Pile)

Max Activating Token Index: 725

Text #10

Max Range: 0.7198. Min Range: -0.7198

Max Act: 0.5013. Min Act: -0.0000

Data Index: 1460527 (The Pile)

Max Activating Token Index: 334

Text #11

Max Range: 0.7198. Min Range: -0.7198

Max Act: 0.5046. Min Act: -0.0000

Data Index: 1081614 (The Pile)

Max Activating Token Index: 1004

Text #12

Max Range: 0.7198. Min Range: -0.7198

Max Act: 0.4923. Min Act: -0.0000

Data Index: 792558 (The Pile)

Max Activating Token Index: 387

Text #13

Max Range: 0.7198. Min Range: -0.7198

Max Act: 0.5008. Min Act: -0.0000

Data Index: 733460 (The Pile)

Max Activating Token Index: 341

Text #14

Max Range: 0.7198. Min Range: -0.7198

Max Act: 0.4983. Min Act: -0.0000

Data Index: 1161109 (The Pile)

Max Activating Token Index: 1021

Text #15

Max Range: 0.7198. Min Range: -0.7198

Max Act: 0.4470. Min Act: -0.0000

Data Index: 1683641 (The Pile)

Max Activating Token Index: 140

Text #16

Max Range: 0.7198. Min Range: -0.7198

Max Act: 0.4739. Min Act: -0.0000

Data Index: 408894 (The Pile)

Max Activating Token Index: 905

Text #17

Max Range: 0.7198. Min Range: -0.7198

Max Act: 0.4722. Min Act: -0.0000

Data Index: 1295777 (The Pile)

Max Activating Token Index: 429

Text #18

Max Range: 0.7198. Min Range: -0.7198

Max Act: 0.4640. Min Act: -0.0000

Data Index: 1172557 (The Pile)

Max Activating Token Index: 295

Text #19

Max Range: 0.7198. Min Range: -0.7198

Max Act: 0.4767. Min Act: -0.0000

Data Index: 1311782 (The Pile)

Max Activating Token Index: 257