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

Dataset: The Pile

Neuron 1111 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: 6.0564. Min Range: -6.0564

Max Act: 6.0564. Min Act: -0.0000

Data Index: 665860 (The Pile)

Max Activating Token Index: 449

Text #1

Max Range: 6.0564. Min Range: -6.0564

Max Act: 5.6596. Min Act: -0.0000

Data Index: 622492 (The Pile)

Max Activating Token Index: 805

Text #2

Max Range: 6.0564. Min Range: -6.0564

Max Act: 5.6777. Min Act: -0.0000

Data Index: 1511276 (The Pile)

Max Activating Token Index: 644

Text #3

Max Range: 6.0564. Min Range: -6.0564

Max Act: 5.6842. Min Act: -0.0000

Data Index: 698258 (The Pile)

Max Activating Token Index: 731

Text #4

Max Range: 6.0564. Min Range: -6.0564

Max Act: 5.5577. Min Act: -0.0000

Data Index: 1764723 (The Pile)

Max Activating Token Index: 696

Text #5

Max Range: 6.0564. Min Range: -6.0564

Max Act: 5.5506. Min Act: -0.0000

Data Index: 1179892 (The Pile)

Max Activating Token Index: 501

Text #6

Max Range: 6.0564. Min Range: -6.0564

Max Act: 5.9137. Min Act: -0.0000

Data Index: 1556994 (The Pile)

Max Activating Token Index: 970

Text #7

Max Range: 6.0564. Min Range: -6.0564

Max Act: 5.6809. Min Act: -0.0000

Data Index: 1378388 (The Pile)

Max Activating Token Index: 487

Text #8

Max Range: 6.0564. Min Range: -6.0564

Max Act: 5.6887. Min Act: -0.0000

Data Index: 366271 (The Pile)

Max Activating Token Index: 762

Text #9

Max Range: 6.0564. Min Range: -6.0564

Max Act: 5.7206. Min Act: -0.0000

Data Index: 1611848 (The Pile)

Max Activating Token Index: 847

Text #10

Max Range: 6.0564. Min Range: -6.0564

Max Act: 5.5030. Min Act: -0.0000

Data Index: 1572269 (The Pile)

Max Activating Token Index: 812

Text #11

Max Range: 6.0564. Min Range: -6.0564

Max Act: 5.9188. Min Act: -0.0000

Data Index: 1050881 (The Pile)

Max Activating Token Index: 1016

Text #12

Max Range: 6.0564. Min Range: -6.0564

Max Act: 5.5750. Min Act: -0.0000

Data Index: 203882 (The Pile)

Max Activating Token Index: 369

Text #13

Max Range: 6.0564. Min Range: -6.0564

Max Act: 5.7760. Min Act: -0.0000

Data Index: 275561 (The Pile)

Max Activating Token Index: 678

Text #14

Max Range: 6.0564. Min Range: -6.0564

Max Act: 5.3255. Min Act: -0.0000

Data Index: 1534333 (The Pile)

Max Activating Token Index: 656

Text #15

Max Range: 6.0564. Min Range: -6.0564

Max Act: 5.1874. Min Act: -0.0000

Data Index: 362329 (The Pile)

Max Activating Token Index: 714

Text #16

Max Range: 6.0564. Min Range: -6.0564

Max Act: 5.3566. Min Act: -0.0000

Data Index: 1176506 (The Pile)

Max Activating Token Index: 716

Text #17

Max Range: 6.0564. Min Range: -6.0564

Max Act: 5.6954. Min Act: -0.0000

Data Index: 882401 (The Pile)

Max Activating Token Index: 644

Text #18

Max Range: 6.0564. Min Range: -6.0564

Max Act: 5.4874. Min Act: -0.0000

Data Index: 1194960 (The Pile)

Max Activating Token Index: 538

Text #19

Max Range: 6.0564. Min Range: -6.0564

Max Act: 5.3154. Min Act: -0.0000

Data Index: 126018 (The Pile)

Max Activating Token Index: 707