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

Dataset: The Pile

Neuron 3063 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: 1.6223. Min Range: -1.6223

Max Act: 1.5889. Min Act: -0.0000

Data Index: 1190007 (The Pile)

Max Activating Token Index: 373

Text #1

Max Range: 1.6223. Min Range: -1.6223

Max Act: 1.5260. Min Act: -0.0000

Data Index: 257037 (The Pile)

Max Activating Token Index: 106

Text #2

Max Range: 1.6223. Min Range: -1.6223

Max Act: 1.6223. Min Act: -0.0000

Data Index: 1068187 (The Pile)

Max Activating Token Index: 290

Text #3

Max Range: 1.6223. Min Range: -1.6223

Max Act: 1.5067. Min Act: -0.0000

Data Index: 878590 (The Pile)

Max Activating Token Index: 606

Text #4

Max Range: 1.6223. Min Range: -1.6223

Max Act: 1.4766. Min Act: -0.0000

Data Index: 1666952 (The Pile)

Max Activating Token Index: 443

Text #5

Max Range: 1.6223. Min Range: -1.6223

Max Act: 1.4812. Min Act: -0.0000

Data Index: 1051095 (The Pile)

Max Activating Token Index: 111

Text #6

Max Range: 1.6223. Min Range: -1.6223

Max Act: 1.4012. Min Act: -0.0000

Data Index: 66884 (The Pile)

Max Activating Token Index: 502

Text #7

Max Range: 1.6223. Min Range: -1.6223

Max Act: 1.4123. Min Act: -0.0000

Data Index: 1442576 (The Pile)

Max Activating Token Index: 74

Text #8

Max Range: 1.6223. Min Range: -1.6223

Max Act: 1.2619. Min Act: -0.0000

Data Index: 1407245 (The Pile)

Max Activating Token Index: 1017

Text #9

Max Range: 1.6223. Min Range: -1.6223

Max Act: 1.2189. Min Act: -0.0000

Data Index: 1418001 (The Pile)

Max Activating Token Index: 53

Text #10

Max Range: 1.6223. Min Range: -1.6223

Max Act: 1.2925. Min Act: -0.0000

Data Index: 341188 (The Pile)

Max Activating Token Index: 133

Text #11

Max Range: 1.6223. Min Range: -1.6223

Max Act: 1.2035. Min Act: -0.0000

Data Index: 1190279 (The Pile)

Max Activating Token Index: 219

Text #12

Max Range: 1.6223. Min Range: -1.6223

Max Act: 1.2521. Min Act: -0.0000

Data Index: 335360 (The Pile)

Max Activating Token Index: 112

Text #13

Max Range: 1.6223. Min Range: -1.6223

Max Act: 1.2073. Min Act: -0.0000

Data Index: 1678723 (The Pile)

Max Activating Token Index: 115

Text #14

Max Range: 1.6223. Min Range: -1.6223

Max Act: 1.2733. Min Act: -0.0000

Data Index: 1787940 (The Pile)

Max Activating Token Index: 679

Text #15

Max Range: 1.6223. Min Range: -1.6223

Max Act: 1.1612. Min Act: -0.0000

Data Index: 419919 (The Pile)

Max Activating Token Index: 957

Text #16

Max Range: 1.6223. Min Range: -1.6223

Max Act: 1.2070. Min Act: -0.0000

Data Index: 1597974 (The Pile)

Max Activating Token Index: 147

Text #17

Max Range: 1.6223. Min Range: -1.6223

Max Act: 1.1667. Min Act: -0.0000

Data Index: 1110196 (The Pile)

Max Activating Token Index: 761

Text #18

Max Range: 1.6223. Min Range: -1.6223

Max Act: 1.1828. Min Act: -0.0000

Data Index: 490052 (The Pile)

Max Activating Token Index: 597

Text #19

Max Range: 1.6223. Min Range: -1.6223

Max Act: 1.2029. Min Act: -0.0000

Data Index: 936498 (The Pile)

Max Activating Token Index: 854