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

Dataset: The Pile

Neuron 2313 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: 1.5731. Min Range: -1.5731

Max Act: 1.3468. Min Act: -0.0000

Data Index: 1388773 (The Pile)

Max Activating Token Index: 345

Text #1

Max Range: 1.5731. Min Range: -1.5731

Max Act: 1.3029. Min Act: -0.0000

Data Index: 151558 (The Pile)

Max Activating Token Index: 140

Text #2

Max Range: 1.5731. Min Range: -1.5731

Max Act: 1.3090. Min Act: -0.0000

Data Index: 1741057 (The Pile)

Max Activating Token Index: 857

Text #3

Max Range: 1.5731. Min Range: -1.5731

Max Act: 1.2693. Min Act: -0.0000

Data Index: 116748 (The Pile)

Max Activating Token Index: 189

Text #4

Max Range: 1.5731. Min Range: -1.5731

Max Act: 1.2821. Min Act: -0.0000

Data Index: 1019454 (The Pile)

Max Activating Token Index: 338

Text #5

Max Range: 1.5731. Min Range: -1.5731

Max Act: 1.1400. Min Act: -0.0000

Data Index: 1702110 (The Pile)

Max Activating Token Index: 170

Text #6

Max Range: 1.5731. Min Range: -1.5731

Max Act: 1.5731. Min Act: -0.0000

Data Index: 285965 (The Pile)

Max Activating Token Index: 985

Text #7

Max Range: 1.5731. Min Range: -1.5731

Max Act: 1.1648. Min Act: -0.0000

Data Index: 1737662 (The Pile)

Max Activating Token Index: 203

Text #8

Max Range: 1.5731. Min Range: -1.5731

Max Act: 1.1087. Min Act: -0.0000

Data Index: 1293961 (The Pile)

Max Activating Token Index: 346

Text #9

Max Range: 1.5731. Min Range: -1.5731

Max Act: 1.2481. Min Act: -0.0000

Data Index: 580175 (The Pile)

Max Activating Token Index: 696

Text #10

Max Range: 1.5731. Min Range: -1.5731

Max Act: 1.1578. Min Act: -0.0000

Data Index: 1789668 (The Pile)

Max Activating Token Index: 173

Text #11

Max Range: 1.5731. Min Range: -1.5731

Max Act: 1.0261. Min Act: -0.0000

Data Index: 394680 (The Pile)

Max Activating Token Index: 558

Text #12

Max Range: 1.5731. Min Range: -1.5731

Max Act: 1.1059. Min Act: -0.0000

Data Index: 452236 (The Pile)

Max Activating Token Index: 169

Text #13

Max Range: 1.5731. Min Range: -1.5731

Max Act: 1.0899. Min Act: -0.0000

Data Index: 1074881 (The Pile)

Max Activating Token Index: 715

Text #14

Max Range: 1.5731. Min Range: -1.5731

Max Act: 0.9964. Min Act: -0.0000

Data Index: 780241 (The Pile)

Max Activating Token Index: 843

Text #15

Max Range: 1.5731. Min Range: -1.5731

Max Act: 1.0726. Min Act: -0.0000

Data Index: 805926 (The Pile)

Max Activating Token Index: 356

Text #16

Max Range: 1.5731. Min Range: -1.5731

Max Act: 1.0394. Min Act: -0.0000

Data Index: 955950 (The Pile)

Max Activating Token Index: 37

Text #17

Max Range: 1.5731. Min Range: -1.5731

Max Act: 1.0615. Min Act: -0.0000

Data Index: 209172 (The Pile)

Max Activating Token Index: 395

Text #18

Max Range: 1.5731. Min Range: -1.5731

Max Act: 1.0784. Min Act: -0.0000

Data Index: 160060 (The Pile)

Max Activating Token Index: 607

Text #19

Max Range: 1.5731. Min Range: -1.5731

Max Act: 1.0508. Min Act: -0.0000

Data Index: 1123663 (The Pile)

Max Activating Token Index: 80