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

Dataset: The Pile

Neuron 2541 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: 1.7111. Min Range: -1.7111

Max Act: 1.7111. Min Act: -0.0000

Data Index: 1662269 (The Pile)

Max Activating Token Index: 746

Text #1

Max Range: 1.7111. Min Range: -1.7111

Max Act: 1.0975. Min Act: -0.0000

Data Index: 1838418 (The Pile)

Max Activating Token Index: 452

Text #2

Max Range: 1.7111. Min Range: -1.7111

Max Act: 1.0622. Min Act: -0.0000

Data Index: 98826 (The Pile)

Max Activating Token Index: 107

Text #3

Max Range: 1.7111. Min Range: -1.7111

Max Act: 1.0557. Min Act: -0.0000

Data Index: 426880 (The Pile)

Max Activating Token Index: 630

Text #4

Max Range: 1.7111. Min Range: -1.7111

Max Act: 1.0214. Min Act: -0.0000

Data Index: 225672 (The Pile)

Max Activating Token Index: 237

Text #5

Max Range: 1.7111. Min Range: -1.7111

Max Act: 0.9636. Min Act: -0.0000

Data Index: 1137078 (The Pile)

Max Activating Token Index: 419

Text #6

Max Range: 1.7111. Min Range: -1.7111

Max Act: 0.9245. Min Act: -0.0000

Data Index: 563659 (The Pile)

Max Activating Token Index: 225

Text #7

Max Range: 1.7111. Min Range: -1.7111

Max Act: 0.9478. Min Act: -0.0000

Data Index: 637155 (The Pile)

Max Activating Token Index: 817

Text #8

Max Range: 1.7111. Min Range: -1.7111

Max Act: 0.9785. Min Act: -0.0000

Data Index: 1954145 (The Pile)

Max Activating Token Index: 686

Text #9

Max Range: 1.7111. Min Range: -1.7111

Max Act: 0.8871. Min Act: -0.0000

Data Index: 987108 (The Pile)

Max Activating Token Index: 530

Text #10

Max Range: 1.7111. Min Range: -1.7111

Max Act: 0.9111. Min Act: -0.0000

Data Index: 12801 (The Pile)

Max Activating Token Index: 199

Text #11

Max Range: 1.7111. Min Range: -1.7111

Max Act: 0.9597. Min Act: -0.0000

Data Index: 932671 (The Pile)

Max Activating Token Index: 225

Text #12

Max Range: 1.7111. Min Range: -1.7111

Max Act: 0.8972. Min Act: -0.0000

Data Index: 634371 (The Pile)

Max Activating Token Index: 343

Text #13

Max Range: 1.7111. Min Range: -1.7111

Max Act: 0.8627. Min Act: -0.0000

Data Index: 648579 (The Pile)

Max Activating Token Index: 258

Text #14

Max Range: 1.7111. Min Range: -1.7111

Max Act: 0.8442. Min Act: -0.0000

Data Index: 1274133 (The Pile)

Max Activating Token Index: 364

Text #15

Max Range: 1.7111. Min Range: -1.7111

Max Act: 0.9140. Min Act: -0.0000

Data Index: 888936 (The Pile)

Max Activating Token Index: 654

Text #16

Max Range: 1.7111. Min Range: -1.7111

Max Act: 0.8624. Min Act: -0.0000

Data Index: 200675 (The Pile)

Max Activating Token Index: 446

Text #17

Max Range: 1.7111. Min Range: -1.7111

Max Act: 0.8845. Min Act: -0.0000

Data Index: 502015 (The Pile)

Max Activating Token Index: 1023

Text #18

Max Range: 1.7111. Min Range: -1.7111

Max Act: 0.8849. Min Act: -0.0000

Data Index: 1090245 (The Pile)

Max Activating Token Index: 79

Text #19

Max Range: 1.7111. Min Range: -1.7111

Max Act: 0.9002. Min Act: -0.0000

Data Index: 1418910 (The Pile)

Max Activating Token Index: 618