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

Dataset: The Pile

Neuron 3325 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.1109. Min Act: -0.0002

Data Index: 1646723 (The Pile)

Max Activating Token Index: 787

Text #1

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0855. Min Act: -0.0002

Data Index: 182319 (The Pile)

Max Activating Token Index: 826

Text #2

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0843. Min Act: -0.0002

Data Index: 881285 (The Pile)

Max Activating Token Index: 34

Text #3

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0832. Min Act: -0.0002

Data Index: 1885361 (The Pile)

Max Activating Token Index: 391

Text #4

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0846. Min Act: -0.0002

Data Index: 192502 (The Pile)

Max Activating Token Index: 1005

Text #5

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0808. Min Act: -0.0002

Data Index: 575524 (The Pile)

Max Activating Token Index: 889

Text #6

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0749. Min Act: -0.0002

Data Index: 967975 (The Pile)

Max Activating Token Index: 947

Text #7

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0749. Min Act: -0.0002

Data Index: 1677180 (The Pile)

Max Activating Token Index: 375

Text #8

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0800. Min Act: -0.0002

Data Index: 1350307 (The Pile)

Max Activating Token Index: 986

Text #9

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0787. Min Act: -0.0002

Data Index: 1831909 (The Pile)

Max Activating Token Index: 612

Text #10

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0736. Min Act: -0.0002

Data Index: 3519 (The Pile)

Max Activating Token Index: 924

Text #11

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0768. Min Act: -0.0002

Data Index: 24185 (The Pile)

Max Activating Token Index: 465

Text #12

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0735. Min Act: -0.0002

Data Index: 448356 (The Pile)

Max Activating Token Index: 275

Text #13

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0764. Min Act: -0.0002

Data Index: 170054 (The Pile)

Max Activating Token Index: 308

Text #14

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0787. Min Act: -0.0002

Data Index: 678378 (The Pile)

Max Activating Token Index: 682

Text #15

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0736. Min Act: -0.0002

Data Index: 1616907 (The Pile)

Max Activating Token Index: 363

Text #16

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0737. Min Act: -0.0002

Data Index: 1086182 (The Pile)

Max Activating Token Index: 63

Text #17

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0686. Min Act: -0.0002

Data Index: 769246 (The Pile)

Max Activating Token Index: 615

Text #18

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0731. Min Act: -0.0002

Data Index: 1874713 (The Pile)

Max Activating Token Index: 312

Text #19

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0685. Min Act: -0.0002

Data Index: 294567 (The Pile)

Max Activating Token Index: 737