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

Dataset: The Pile

Neuron 3701 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: 0.5011. Min Range: -0.5011

Max Act: 0.5011. Min Act: -0.0000

Data Index: 1704948 (The Pile)

Max Activating Token Index: 454

Text #1

Max Range: 0.5011. Min Range: -0.5011

Max Act: 0.4338. Min Act: 0.0000

Data Index: 1088233 (The Pile)

Max Activating Token Index: 408

Text #2

Max Range: 0.5011. Min Range: -0.5011

Max Act: 0.3785. Min Act: -0.0000

Data Index: 1370121 (The Pile)

Max Activating Token Index: 827

Text #3

Max Range: 0.5011. Min Range: -0.5011

Max Act: 0.4201. Min Act: -0.0000

Data Index: 1830748 (The Pile)

Max Activating Token Index: 287

Text #4

Max Range: 0.5011. Min Range: -0.5011

Max Act: 0.4259. Min Act: -0.0000

Data Index: 992638 (The Pile)

Max Activating Token Index: 102

Text #5

Max Range: 0.5011. Min Range: -0.5011

Max Act: 0.4067. Min Act: -0.0000

Data Index: 1394870 (The Pile)

Max Activating Token Index: 335

Text #6

Max Range: 0.5011. Min Range: -0.5011

Max Act: 0.3892. Min Act: 0.0000

Data Index: 140951 (The Pile)

Max Activating Token Index: 862

Text #7

Max Range: 0.5011. Min Range: -0.5011

Max Act: 0.4258. Min Act: -0.0000

Data Index: 1492805 (The Pile)

Max Activating Token Index: 801

Text #8

Max Range: 0.5011. Min Range: -0.5011

Max Act: 0.3437. Min Act: -0.0000

Data Index: 1841008 (The Pile)

Max Activating Token Index: 828

Text #9

Max Range: 0.5011. Min Range: -0.5011

Max Act: 0.3807. Min Act: -0.0000

Data Index: 1263448 (The Pile)

Max Activating Token Index: 582

Text #10

Max Range: 0.5011. Min Range: -0.5011

Max Act: 0.3775. Min Act: 0.0000

Data Index: 1245356 (The Pile)

Max Activating Token Index: 863

Text #11

Max Range: 0.5011. Min Range: -0.5011

Max Act: 0.3573. Min Act: -0.0000

Data Index: 1145603 (The Pile)

Max Activating Token Index: 706

Text #12

Max Range: 0.5011. Min Range: -0.5011

Max Act: 0.3723. Min Act: -0.0000

Data Index: 153789 (The Pile)

Max Activating Token Index: 636

Text #13

Max Range: 0.5011. Min Range: -0.5011

Max Act: 0.3705. Min Act: -0.0000

Data Index: 368303 (The Pile)

Max Activating Token Index: 461

Text #14

Max Range: 0.5011. Min Range: -0.5011

Max Act: 0.3855. Min Act: -0.0000

Data Index: 95036 (The Pile)

Max Activating Token Index: 824

Text #15

Max Range: 0.5011. Min Range: -0.5011

Max Act: 0.3596. Min Act: -0.0000

Data Index: 1481976 (The Pile)

Max Activating Token Index: 863

Text #16

Max Range: 0.5011. Min Range: -0.5011

Max Act: 0.3734. Min Act: -0.0000

Data Index: 1677064 (The Pile)

Max Activating Token Index: 726

Text #17

Max Range: 0.5011. Min Range: -0.5011

Max Act: 0.3521. Min Act: 0.0000

Data Index: 205855 (The Pile)

Max Activating Token Index: 443

Text #18

Max Range: 0.5011. Min Range: -0.5011

Max Act: 0.3867. Min Act: -0.0000

Data Index: 210929 (The Pile)

Max Activating Token Index: 713

Text #19

Max Range: 0.5011. Min Range: -0.5011

Max Act: 0.3422. Min Act: -0.0000

Data Index: 1508931 (The Pile)

Max Activating Token Index: 574