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

Dataset: The Pile

Neuron 4929 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2797. Min Range: -1.2797

Max Act: 1.2797. Min Act: -0.0000

Data Index: 1854701 (The Pile)

Max Activating Token Index: 688

Text #1

Max Range: 1.2797. Min Range: -1.2797

Max Act: 0.9543. Min Act: 0.0000

Data Index: 644785 (The Pile)

Max Activating Token Index: 393

Text #2

Max Range: 1.2797. Min Range: -1.2797

Max Act: 0.9180. Min Act: -0.0000

Data Index: 1670920 (The Pile)

Max Activating Token Index: 646

Text #3

Max Range: 1.2797. Min Range: -1.2797

Max Act: 0.9349. Min Act: -0.0000

Data Index: 128726 (The Pile)

Max Activating Token Index: 1022

Text #4

Max Range: 1.2797. Min Range: -1.2797

Max Act: 0.9169. Min Act: -0.0000

Data Index: 586995 (The Pile)

Max Activating Token Index: 587

Text #5

Max Range: 1.2797. Min Range: -1.2797

Max Act: 0.7887. Min Act: -0.0000

Data Index: 197758 (The Pile)

Max Activating Token Index: 940

Text #6

Max Range: 1.2797. Min Range: -1.2797

Max Act: 0.8467. Min Act: -0.0000

Data Index: 1430641 (The Pile)

Max Activating Token Index: 996

Text #7

Max Range: 1.2797. Min Range: -1.2797

Max Act: 0.8543. Min Act: -0.0000

Data Index: 316242 (The Pile)

Max Activating Token Index: 794

Text #8

Max Range: 1.2797. Min Range: -1.2797

Max Act: 0.9268. Min Act: -0.0000

Data Index: 1937810 (The Pile)

Max Activating Token Index: 760

Text #9

Max Range: 1.2797. Min Range: -1.2797

Max Act: 0.8109. Min Act: -0.0000

Data Index: 1831812 (The Pile)

Max Activating Token Index: 379

Text #10

Max Range: 1.2797. Min Range: -1.2797

Max Act: 0.7478. Min Act: -0.0000

Data Index: 1575753 (The Pile)

Max Activating Token Index: 690

Text #11

Max Range: 1.2797. Min Range: -1.2797

Max Act: 0.6357. Min Act: -0.0000

Data Index: 195418 (The Pile)

Max Activating Token Index: 862

Text #12

Max Range: 1.2797. Min Range: -1.2797

Max Act: 0.6892. Min Act: -0.0000

Data Index: 168651 (The Pile)

Max Activating Token Index: 893

Text #13

Max Range: 1.2797. Min Range: -1.2797

Max Act: 0.7586. Min Act: -0.0000

Data Index: 824355 (The Pile)

Max Activating Token Index: 755

Text #14

Max Range: 1.2797. Min Range: -1.2797

Max Act: 0.6544. Min Act: -0.0000

Data Index: 620149 (The Pile)

Max Activating Token Index: 456

Text #15

Max Range: 1.2797. Min Range: -1.2797

Max Act: 0.8186. Min Act: -0.0000

Data Index: 1577223 (The Pile)

Max Activating Token Index: 664

Text #16

Max Range: 1.2797. Min Range: -1.2797

Max Act: 0.6596. Min Act: -0.0000

Data Index: 354798 (The Pile)

Max Activating Token Index: 839

Text #17

Max Range: 1.2797. Min Range: -1.2797

Max Act: 0.6427. Min Act: 0.0000

Data Index: 1295016 (The Pile)

Max Activating Token Index: 484

Text #18

Max Range: 1.2797. Min Range: -1.2797

Max Act: 0.6346. Min Act: -0.0000

Data Index: 1522870 (The Pile)

Max Activating Token Index: 62

Text #19

Max Range: 1.2797. Min Range: -1.2797

Max Act: 0.6203. Min Act: -0.0000

Data Index: 1025317 (The Pile)

Max Activating Token Index: 232