Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3714 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.3269. Min Range: -1.3269

Max Act: 1.3269. Min Act: -0.0000

Data Index: 1978346 (The Pile)

Max Activating Token Index: 436

Text #1

Max Range: 1.3269. Min Range: -1.3269

Max Act: 1.1025. Min Act: -0.0000

Data Index: 1942697 (The Pile)

Max Activating Token Index: 789

Text #2

Max Range: 1.3269. Min Range: -1.3269

Max Act: 1.1846. Min Act: -0.0000

Data Index: 1917496 (The Pile)

Max Activating Token Index: 138

Text #3

Max Range: 1.3269. Min Range: -1.3269

Max Act: 1.0383. Min Act: -0.0000

Data Index: 747905 (The Pile)

Max Activating Token Index: 782

Text #4

Max Range: 1.3269. Min Range: -1.3269

Max Act: 0.9758. Min Act: -0.0000

Data Index: 466065 (The Pile)

Max Activating Token Index: 496

Text #5

Max Range: 1.3269. Min Range: -1.3269

Max Act: 1.0279. Min Act: -0.0000

Data Index: 1550487 (The Pile)

Max Activating Token Index: 294

Text #6

Max Range: 1.3269. Min Range: -1.3269

Max Act: 0.9913. Min Act: -0.0000

Data Index: 634660 (The Pile)

Max Activating Token Index: 334

Text #7

Max Range: 1.3269. Min Range: -1.3269

Max Act: 0.9412. Min Act: -0.0000

Data Index: 290238 (The Pile)

Max Activating Token Index: 485

Text #8

Max Range: 1.3269. Min Range: -1.3269

Max Act: 0.9350. Min Act: -0.0000

Data Index: 1125070 (The Pile)

Max Activating Token Index: 887

Text #9

Max Range: 1.3269. Min Range: -1.3269

Max Act: 0.9287. Min Act: -0.0000

Data Index: 1691159 (The Pile)

Max Activating Token Index: 878

Text #10

Max Range: 1.3269. Min Range: -1.3269

Max Act: 0.8854. Min Act: -0.0000

Data Index: 1275861 (The Pile)

Max Activating Token Index: 835

Text #11

Max Range: 1.3269. Min Range: -1.3269

Max Act: 0.8817. Min Act: -0.0000

Data Index: 108375 (The Pile)

Max Activating Token Index: 46

Text #12

Max Range: 1.3269. Min Range: -1.3269

Max Act: 0.9029. Min Act: -0.0000

Data Index: 824775 (The Pile)

Max Activating Token Index: 855

Text #13

Max Range: 1.3269. Min Range: -1.3269

Max Act: 0.8894. Min Act: -0.0000

Data Index: 1148758 (The Pile)

Max Activating Token Index: 774

Text #14

Max Range: 1.3269. Min Range: -1.3269

Max Act: 0.8624. Min Act: -0.0000

Data Index: 1069273 (The Pile)

Max Activating Token Index: 164

Text #15

Max Range: 1.3269. Min Range: -1.3269

Max Act: 0.7749. Min Act: -0.0000

Data Index: 1157422 (The Pile)

Max Activating Token Index: 124

Text #16

Max Range: 1.3269. Min Range: -1.3269

Max Act: 0.8847. Min Act: -0.0000

Data Index: 887349 (The Pile)

Max Activating Token Index: 935

Text #17

Max Range: 1.3269. Min Range: -1.3269

Max Act: 0.8603. Min Act: -0.0000

Data Index: 1075295 (The Pile)

Max Activating Token Index: 256

Text #18

Max Range: 1.3269. Min Range: -1.3269

Max Act: 0.8572. Min Act: -0.0000

Data Index: 1291228 (The Pile)

Max Activating Token Index: 633

Text #19

Max Range: 1.3269. Min Range: -1.3269

Max Act: 0.8578. Min Act: -0.0000

Data Index: 763633 (The Pile)

Max Activating Token Index: 872