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

Dataset: The Pile

Neuron 1849 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: 1.7191. Min Range: -1.7191

Max Act: 1.7063. Min Act: -0.0000

Data Index: 1508737 (The Pile)

Max Activating Token Index: 163

Text #1

Max Range: 1.7191. Min Range: -1.7191

Max Act: 1.5820. Min Act: -0.0000

Data Index: 388683 (The Pile)

Max Activating Token Index: 875

Text #2

Max Range: 1.7191. Min Range: -1.7191

Max Act: 1.7191. Min Act: -0.0000

Data Index: 1429886 (The Pile)

Max Activating Token Index: 438

Text #3

Max Range: 1.7191. Min Range: -1.7191

Max Act: 1.6075. Min Act: -0.0000

Data Index: 969097 (The Pile)

Max Activating Token Index: 853

Text #4

Max Range: 1.7191. Min Range: -1.7191

Max Act: 1.5305. Min Act: -0.0000

Data Index: 1839351 (The Pile)

Max Activating Token Index: 644

Text #5

Max Range: 1.7191. Min Range: -1.7191

Max Act: 1.5184. Min Act: -0.0000

Data Index: 1069015 (The Pile)

Max Activating Token Index: 438

Text #6

Max Range: 1.7191. Min Range: -1.7191

Max Act: 1.5799. Min Act: -0.0000

Data Index: 1456812 (The Pile)

Max Activating Token Index: 682

Text #7

Max Range: 1.7191. Min Range: -1.7191

Max Act: 1.4350. Min Act: -0.0000

Data Index: 1062560 (The Pile)

Max Activating Token Index: 893

Text #8

Max Range: 1.7191. Min Range: -1.7191

Max Act: 1.3706. Min Act: -0.0000

Data Index: 150990 (The Pile)

Max Activating Token Index: 781

Text #9

Max Range: 1.7191. Min Range: -1.7191

Max Act: 1.3156. Min Act: -0.0000

Data Index: 902024 (The Pile)

Max Activating Token Index: 837

Text #10

Max Range: 1.7191. Min Range: -1.7191

Max Act: 1.4190. Min Act: -0.0000

Data Index: 716060 (The Pile)

Max Activating Token Index: 656

Text #11

Max Range: 1.7191. Min Range: -1.7191

Max Act: 1.3455. Min Act: -0.0000

Data Index: 80808 (The Pile)

Max Activating Token Index: 657

Text #12

Max Range: 1.7191. Min Range: -1.7191

Max Act: 1.3348. Min Act: -0.0000

Data Index: 1247748 (The Pile)

Max Activating Token Index: 153

Text #13

Max Range: 1.7191. Min Range: -1.7191

Max Act: 1.5552. Min Act: -0.0000

Data Index: 344190 (The Pile)

Max Activating Token Index: 930

Text #14

Max Range: 1.7191. Min Range: -1.7191

Max Act: 1.4115. Min Act: -0.0000

Data Index: 976588 (The Pile)

Max Activating Token Index: 555

Text #15

Max Range: 1.7191. Min Range: -1.7191

Max Act: 1.3372. Min Act: -0.0000

Data Index: 860268 (The Pile)

Max Activating Token Index: 573

Text #16

Max Range: 1.7191. Min Range: -1.7191

Max Act: 1.4046. Min Act: -0.0000

Data Index: 229179 (The Pile)

Max Activating Token Index: 517

Text #17

Max Range: 1.7191. Min Range: -1.7191

Max Act: 1.3816. Min Act: -0.0000

Data Index: 1614425 (The Pile)

Max Activating Token Index: 990

Text #18

Max Range: 1.7191. Min Range: -1.7191

Max Act: 1.3839. Min Act: -0.0000

Data Index: 458323 (The Pile)

Max Activating Token Index: 868

Text #19

Max Range: 1.7191. Min Range: -1.7191

Max Act: 1.3663. Min Act: -0.0000

Data Index: 912192 (The Pile)

Max Activating Token Index: 422