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

Dataset: The Pile

Neuron 4899 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: 0.3149. Min Range: -0.3149

Max Act: 0.3149. Min Act: -0.0000

Data Index: 1767279 (The Pile)

Max Activating Token Index: 705

Text #1

Max Range: 0.3149. Min Range: -0.3149

Max Act: 0.3010. Min Act: -0.0000

Data Index: 1739928 (The Pile)

Max Activating Token Index: 794

Text #2

Max Range: 0.3149. Min Range: -0.3149

Max Act: 0.2856. Min Act: -0.0000

Data Index: 396783 (The Pile)

Max Activating Token Index: 95

Text #3

Max Range: 0.3149. Min Range: -0.3149

Max Act: 0.3027. Min Act: -0.0000

Data Index: 723656 (The Pile)

Max Activating Token Index: 248

Text #4

Max Range: 0.3149. Min Range: -0.3149

Max Act: 0.2618. Min Act: -0.0000

Data Index: 719573 (The Pile)

Max Activating Token Index: 703

Text #5

Max Range: 0.3149. Min Range: -0.3149

Max Act: 0.2651. Min Act: -0.0000

Data Index: 1035118 (The Pile)

Max Activating Token Index: 729

Text #6

Max Range: 0.3149. Min Range: -0.3149

Max Act: 0.2528. Min Act: -0.0000

Data Index: 283117 (The Pile)

Max Activating Token Index: 875

Text #7

Max Range: 0.3149. Min Range: -0.3149

Max Act: 0.2585. Min Act: -0.0000

Data Index: 398890 (The Pile)

Max Activating Token Index: 719

Text #8

Max Range: 0.3149. Min Range: -0.3149

Max Act: 0.2229. Min Act: -0.0000

Data Index: 1243859 (The Pile)

Max Activating Token Index: 613

Text #9

Max Range: 0.3149. Min Range: -0.3149

Max Act: 0.2097. Min Act: -0.0000

Data Index: 1584067 (The Pile)

Max Activating Token Index: 1019

Text #10

Max Range: 0.3149. Min Range: -0.3149

Max Act: 0.2169. Min Act: -0.0000

Data Index: 1653437 (The Pile)

Max Activating Token Index: 562

Text #11

Max Range: 0.3149. Min Range: -0.3149

Max Act: 0.2220. Min Act: -0.0000

Data Index: 1343774 (The Pile)

Max Activating Token Index: 855

Text #12

Max Range: 0.3149. Min Range: -0.3149

Max Act: 0.2148. Min Act: -0.0000

Data Index: 789850 (The Pile)

Max Activating Token Index: 218

Text #13

Max Range: 0.3149. Min Range: -0.3149

Max Act: 0.2204. Min Act: -0.0000

Data Index: 814045 (The Pile)

Max Activating Token Index: 225

Text #14

Max Range: 0.3149. Min Range: -0.3149

Max Act: 0.2118. Min Act: -0.0000

Data Index: 881706 (The Pile)

Max Activating Token Index: 38

Text #15

Max Range: 0.3149. Min Range: -0.3149

Max Act: 0.2203. Min Act: -0.0000

Data Index: 583305 (The Pile)

Max Activating Token Index: 281

Text #16

Max Range: 0.3149. Min Range: -0.3149

Max Act: 0.2309. Min Act: -0.0000

Data Index: 518351 (The Pile)

Max Activating Token Index: 832

Text #17

Max Range: 0.3149. Min Range: -0.3149

Max Act: 0.2010. Min Act: -0.0000

Data Index: 527226 (The Pile)

Max Activating Token Index: 756

Text #18

Max Range: 0.3149. Min Range: -0.3149

Max Act: 0.2033. Min Act: -0.0000

Data Index: 1754489 (The Pile)

Max Activating Token Index: 509

Text #19

Max Range: 0.3149. Min Range: -0.3149

Max Act: 0.2046. Min Act: -0.0000

Data Index: 594562 (The Pile)

Max Activating Token Index: 319