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

Dataset: The Pile

Neuron 3068 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6713. Min Range: -0.6713

Max Act: 0.6713. Min Act: -0.0000

Data Index: 635906 (The Pile)

Max Activating Token Index: 608

Text #1

Max Range: 0.6713. Min Range: -0.6713

Max Act: 0.6115. Min Act: -0.0000

Data Index: 437397 (The Pile)

Max Activating Token Index: 347

Text #2

Max Range: 0.6713. Min Range: -0.6713

Max Act: 0.6231. Min Act: -0.0000

Data Index: 280976 (The Pile)

Max Activating Token Index: 29

Text #3

Max Range: 0.6713. Min Range: -0.6713

Max Act: 0.5476. Min Act: -0.0000

Data Index: 798010 (The Pile)

Max Activating Token Index: 528

Text #4

Max Range: 0.6713. Min Range: -0.6713

Max Act: 0.5922. Min Act: -0.0000

Data Index: 758866 (The Pile)

Max Activating Token Index: 130

Text #5

Max Range: 0.6713. Min Range: -0.6713

Max Act: 0.5482. Min Act: -0.0000

Data Index: 1572872 (The Pile)

Max Activating Token Index: 238

Text #6

Max Range: 0.6713. Min Range: -0.6713

Max Act: 0.5208. Min Act: -0.0000

Data Index: 296830 (The Pile)

Max Activating Token Index: 856

Text #7

Max Range: 0.6713. Min Range: -0.6713

Max Act: 0.4964. Min Act: -0.0000

Data Index: 871291 (The Pile)

Max Activating Token Index: 122

Text #8

Max Range: 0.6713. Min Range: -0.6713

Max Act: 0.4797. Min Act: -0.0000

Data Index: 788153 (The Pile)

Max Activating Token Index: 676

Text #9

Max Range: 0.6713. Min Range: -0.6713

Max Act: 0.4697. Min Act: -0.0000

Data Index: 1052890 (The Pile)

Max Activating Token Index: 678

Text #10

Max Range: 0.6713. Min Range: -0.6713

Max Act: 0.4780. Min Act: -0.0000

Data Index: 18602 (The Pile)

Max Activating Token Index: 682

Text #11

Max Range: 0.6713. Min Range: -0.6713

Max Act: 0.4502. Min Act: -0.0000

Data Index: 1105304 (The Pile)

Max Activating Token Index: 483

Text #12

Max Range: 0.6713. Min Range: -0.6713

Max Act: 0.4246. Min Act: -0.0000

Data Index: 835893 (The Pile)

Max Activating Token Index: 238

Text #13

Max Range: 0.6713. Min Range: -0.6713

Max Act: 0.4436. Min Act: -0.0000

Data Index: 956674 (The Pile)

Max Activating Token Index: 698

Text #14

Max Range: 0.6713. Min Range: -0.6713

Max Act: 0.4164. Min Act: -0.0000

Data Index: 1700542 (The Pile)

Max Activating Token Index: 591

Text #15

Max Range: 0.6713. Min Range: -0.6713

Max Act: 0.4312. Min Act: -0.0000

Data Index: 1446682 (The Pile)

Max Activating Token Index: 97

Text #16

Max Range: 0.6713. Min Range: -0.6713

Max Act: 0.4155. Min Act: -0.0000

Data Index: 1692198 (The Pile)

Max Activating Token Index: 595

Text #17

Max Range: 0.6713. Min Range: -0.6713

Max Act: 0.5024. Min Act: -0.0000

Data Index: 907531 (The Pile)

Max Activating Token Index: 789

Text #18

Max Range: 0.6713. Min Range: -0.6713

Max Act: 0.4359. Min Act: -0.0000

Data Index: 1139685 (The Pile)

Max Activating Token Index: 30

Text #19

Max Range: 0.6713. Min Range: -0.6713

Max Act: 0.4359. Min Act: -0.0000

Data Index: 206729 (The Pile)

Max Activating Token Index: 288