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

Dataset: The Pile

Neuron 2740 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: 1.2998. Min Range: -1.2998

Max Act: 1.2998. Min Act: -0.0000

Data Index: 607964 (The Pile)

Max Activating Token Index: 823

Text #1

Max Range: 1.2998. Min Range: -1.2998

Max Act: 1.2836. Min Act: -0.0000

Data Index: 1218092 (The Pile)

Max Activating Token Index: 643

Text #2

Max Range: 1.2998. Min Range: -1.2998

Max Act: 1.1737. Min Act: -0.0000

Data Index: 1584654 (The Pile)

Max Activating Token Index: 1013

Text #3

Max Range: 1.2998. Min Range: -1.2998

Max Act: 1.2772. Min Act: -0.0000

Data Index: 543865 (The Pile)

Max Activating Token Index: 312

Text #4

Max Range: 1.2998. Min Range: -1.2998

Max Act: 1.1550. Min Act: -0.0000

Data Index: 1103116 (The Pile)

Max Activating Token Index: 800

Text #5

Max Range: 1.2998. Min Range: -1.2998

Max Act: 1.0802. Min Act: -0.0000

Data Index: 285247 (The Pile)

Max Activating Token Index: 608

Text #6

Max Range: 1.2998. Min Range: -1.2998

Max Act: 0.9283. Min Act: -0.0000

Data Index: 138622 (The Pile)

Max Activating Token Index: 1008

Text #7

Max Range: 1.2998. Min Range: -1.2998

Max Act: 0.9194. Min Act: -0.0000

Data Index: 1845714 (The Pile)

Max Activating Token Index: 901

Text #8

Max Range: 1.2998. Min Range: -1.2998

Max Act: 0.9410. Min Act: -0.0000

Data Index: 939145 (The Pile)

Max Activating Token Index: 868

Text #9

Max Range: 1.2998. Min Range: -1.2998

Max Act: 0.9411. Min Act: -0.0000

Data Index: 727604 (The Pile)

Max Activating Token Index: 793

Text #10

Max Range: 1.2998. Min Range: -1.2998

Max Act: 0.8273. Min Act: -0.0000

Data Index: 1862809 (The Pile)

Max Activating Token Index: 618

Text #11

Max Range: 1.2998. Min Range: -1.2998

Max Act: 1.0275. Min Act: -0.0000

Data Index: 919907 (The Pile)

Max Activating Token Index: 91

Text #12

Max Range: 1.2998. Min Range: -1.2998

Max Act: 0.8259. Min Act: -0.0000

Data Index: 1564180 (The Pile)

Max Activating Token Index: 981

Text #13

Max Range: 1.2998. Min Range: -1.2998

Max Act: 1.0071. Min Act: -0.0000

Data Index: 662009 (The Pile)

Max Activating Token Index: 913

Text #14

Max Range: 1.2998. Min Range: -1.2998

Max Act: 0.9296. Min Act: -0.0000

Data Index: 1227462 (The Pile)

Max Activating Token Index: 723

Text #15

Max Range: 1.2998. Min Range: -1.2998

Max Act: 0.8639. Min Act: -0.0000

Data Index: 911622 (The Pile)

Max Activating Token Index: 504

Text #16

Max Range: 1.2998. Min Range: -1.2998

Max Act: 0.8822. Min Act: -0.0000

Data Index: 105573 (The Pile)

Max Activating Token Index: 741

Text #17

Max Range: 1.2998. Min Range: -1.2998

Max Act: 0.8570. Min Act: -0.0000

Data Index: 1189309 (The Pile)

Max Activating Token Index: 760

Text #18

Max Range: 1.2998. Min Range: -1.2998

Max Act: 0.8938. Min Act: -0.0000

Data Index: 246260 (The Pile)

Max Activating Token Index: 707

Text #19

Max Range: 1.2998. Min Range: -1.2998

Max Act: 0.8648. Min Act: -0.0000

Data Index: 794609 (The Pile)

Max Activating Token Index: 417