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

Dataset: The Pile

Neuron 2691 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3109. Min Range: -0.3109

Max Act: 0.2820. Min Act: -0.0000

Data Index: 372028 (The Pile)

Max Activating Token Index: 530

Text #1

Max Range: 0.3109. Min Range: -0.3109

Max Act: 0.3109. Min Act: -0.0000

Data Index: 1782528 (The Pile)

Max Activating Token Index: 936

Text #2

Max Range: 0.3109. Min Range: -0.3109

Max Act: 0.2970. Min Act: -0.0000

Data Index: 681805 (The Pile)

Max Activating Token Index: 998

Text #3

Max Range: 0.3109. Min Range: -0.3109

Max Act: 0.2856. Min Act: -0.0000

Data Index: 455047 (The Pile)

Max Activating Token Index: 111

Text #4

Max Range: 0.3109. Min Range: -0.3109

Max Act: 0.2688. Min Act: -0.0000

Data Index: 1509607 (The Pile)

Max Activating Token Index: 628

Text #5

Max Range: 0.3109. Min Range: -0.3109

Max Act: 0.2570. Min Act: -0.0000

Data Index: 1436374 (The Pile)

Max Activating Token Index: 775

Text #6

Max Range: 0.3109. Min Range: -0.3109

Max Act: 0.2856. Min Act: -0.0000

Data Index: 1213694 (The Pile)

Max Activating Token Index: 708

Text #7

Max Range: 0.3109. Min Range: -0.3109

Max Act: 0.2750. Min Act: -0.0000

Data Index: 1956995 (The Pile)

Max Activating Token Index: 884

Text #8

Max Range: 0.3109. Min Range: -0.3109

Max Act: 0.2726. Min Act: -0.0000

Data Index: 1780863 (The Pile)

Max Activating Token Index: 237

Text #9

Max Range: 0.3109. Min Range: -0.3109

Max Act: 0.2477. Min Act: -0.0000

Data Index: 794807 (The Pile)

Max Activating Token Index: 880

Text #10

Max Range: 0.3109. Min Range: -0.3109

Max Act: 0.2809. Min Act: -0.0000

Data Index: 738009 (The Pile)

Max Activating Token Index: 134

Text #11

Max Range: 0.3109. Min Range: -0.3109

Max Act: 0.2726. Min Act: -0.0000

Data Index: 1833733 (The Pile)

Max Activating Token Index: 248

Text #12

Max Range: 0.3109. Min Range: -0.3109

Max Act: 0.2433. Min Act: -0.0000

Data Index: 850037 (The Pile)

Max Activating Token Index: 1022

Text #13

Max Range: 0.3109. Min Range: -0.3109

Max Act: 0.2990. Min Act: -0.0000

Data Index: 1183954 (The Pile)

Max Activating Token Index: 533

Text #14

Max Range: 0.3109. Min Range: -0.3109

Max Act: 0.2823. Min Act: -0.0000

Data Index: 1744874 (The Pile)

Max Activating Token Index: 720

Text #15

Max Range: 0.3109. Min Range: -0.3109

Max Act: 0.2567. Min Act: -0.0000

Data Index: 813836 (The Pile)

Max Activating Token Index: 444

Text #16

Max Range: 0.3109. Min Range: -0.3109

Max Act: 0.2679. Min Act: -0.0000

Data Index: 1168349 (The Pile)

Max Activating Token Index: 866

Text #17

Max Range: 0.3109. Min Range: -0.3109

Max Act: 0.2558. Min Act: -0.0000

Data Index: 645022 (The Pile)

Max Activating Token Index: 156

Text #18

Max Range: 0.3109. Min Range: -0.3109

Max Act: 0.2746. Min Act: -0.0000

Data Index: 1181345 (The Pile)

Max Activating Token Index: 244

Text #19

Max Range: 0.3109. Min Range: -0.3109

Max Act: 0.2698. Min Act: -0.0000

Data Index: 1766526 (The Pile)

Max Activating Token Index: 281