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

Dataset: The Pile

Neuron 1451 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7971. Min Range: -0.7971

Max Act: 0.7971. Min Act: -0.0000

Data Index: 639112 (The Pile)

Max Activating Token Index: 102

Text #1

Max Range: 0.7971. Min Range: -0.7971

Max Act: 0.4819. Min Act: -0.0000

Data Index: 379602 (The Pile)

Max Activating Token Index: 599

Text #2

Max Range: 0.7971. Min Range: -0.7971

Max Act: 0.4953. Min Act: -0.0000

Data Index: 707166 (The Pile)

Max Activating Token Index: 979

Text #3

Max Range: 0.7971. Min Range: -0.7971

Max Act: 0.4931. Min Act: -0.0000

Data Index: 1414517 (The Pile)

Max Activating Token Index: 343

Text #4

Max Range: 0.7971. Min Range: -0.7971

Max Act: 0.4256. Min Act: -0.0000

Data Index: 268169 (The Pile)

Max Activating Token Index: 825

Text #5

Max Range: 0.7971. Min Range: -0.7971

Max Act: 0.3925. Min Act: -0.0000

Data Index: 591973 (The Pile)

Max Activating Token Index: 657

Text #6

Max Range: 0.7971. Min Range: -0.7971

Max Act: 0.5068. Min Act: -0.0000

Data Index: 603276 (The Pile)

Max Activating Token Index: 673

Text #7

Max Range: 0.7971. Min Range: -0.7971

Max Act: 0.4315. Min Act: -0.0000

Data Index: 1141770 (The Pile)

Max Activating Token Index: 310

Text #8

Max Range: 0.7971. Min Range: -0.7971

Max Act: 0.4251. Min Act: -0.0000

Data Index: 901907 (The Pile)

Max Activating Token Index: 221

Text #9

Max Range: 0.7971. Min Range: -0.7971

Max Act: 0.4193. Min Act: -0.0000

Data Index: 1958339 (The Pile)

Max Activating Token Index: 31

Text #10

Max Range: 0.7971. Min Range: -0.7971

Max Act: 0.4377. Min Act: -0.0000

Data Index: 543775 (The Pile)

Max Activating Token Index: 223

Text #11

Max Range: 0.7971. Min Range: -0.7971

Max Act: 0.3711. Min Act: -0.0000

Data Index: 1195740 (The Pile)

Max Activating Token Index: 582

Text #12

Max Range: 0.7971. Min Range: -0.7971

Max Act: 0.4149. Min Act: -0.0000

Data Index: 1077803 (The Pile)

Max Activating Token Index: 98

Text #13

Max Range: 0.7971. Min Range: -0.7971

Max Act: 0.3773. Min Act: -0.0000

Data Index: 1340124 (The Pile)

Max Activating Token Index: 612

Text #14

Max Range: 0.7971. Min Range: -0.7971

Max Act: 0.3900. Min Act: -0.0000

Data Index: 244008 (The Pile)

Max Activating Token Index: 24

Text #15

Max Range: 0.7971. Min Range: -0.7971

Max Act: 0.4018. Min Act: -0.0000

Data Index: 490454 (The Pile)

Max Activating Token Index: 760

Text #16

Max Range: 0.7971. Min Range: -0.7971

Max Act: 0.3967. Min Act: -0.0000

Data Index: 1302771 (The Pile)

Max Activating Token Index: 297

Text #17

Max Range: 0.7971. Min Range: -0.7971

Max Act: 0.4212. Min Act: -0.0000

Data Index: 1125523 (The Pile)

Max Activating Token Index: 726

Text #18

Max Range: 0.7971. Min Range: -0.7971

Max Act: 0.3852. Min Act: -0.0000

Data Index: 1005421 (The Pile)

Max Activating Token Index: 283

Text #19

Max Range: 0.7971. Min Range: -0.7971

Max Act: 0.3930. Min Act: -0.0000

Data Index: 615147 (The Pile)

Max Activating Token Index: 368