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

Dataset: The Pile

Neuron 4554 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: 1.5989. Min Range: -1.5989

Max Act: 1.5092. Min Act: -0.0000

Data Index: 1537540 (The Pile)

Max Activating Token Index: 387

Text #1

Max Range: 1.5989. Min Range: -1.5989

Max Act: 1.5989. Min Act: -0.0000

Data Index: 479953 (The Pile)

Max Activating Token Index: 156

Text #2

Max Range: 1.5989. Min Range: -1.5989

Max Act: 1.4645. Min Act: -0.0000

Data Index: 1780746 (The Pile)

Max Activating Token Index: 70

Text #3

Max Range: 1.5989. Min Range: -1.5989

Max Act: 1.4530. Min Act: -0.0000

Data Index: 1192067 (The Pile)

Max Activating Token Index: 26

Text #4

Max Range: 1.5989. Min Range: -1.5989

Max Act: 1.4163. Min Act: -0.0000

Data Index: 838363 (The Pile)

Max Activating Token Index: 325

Text #5

Max Range: 1.5989. Min Range: -1.5989

Max Act: 1.4044. Min Act: -0.0000

Data Index: 1346299 (The Pile)

Max Activating Token Index: 814

Text #6

Max Range: 1.5989. Min Range: -1.5989

Max Act: 1.3957. Min Act: -0.0000

Data Index: 1636887 (The Pile)

Max Activating Token Index: 459

Text #7

Max Range: 1.5989. Min Range: -1.5989

Max Act: 1.3953. Min Act: -0.0000

Data Index: 1836079 (The Pile)

Max Activating Token Index: 469

Text #8

Max Range: 1.5989. Min Range: -1.5989

Max Act: 1.3856. Min Act: -0.0000

Data Index: 1165247 (The Pile)

Max Activating Token Index: 689

Text #9

Max Range: 1.5989. Min Range: -1.5989

Max Act: 1.3672. Min Act: -0.0000

Data Index: 1135448 (The Pile)

Max Activating Token Index: 605

Text #10

Max Range: 1.5989. Min Range: -1.5989

Max Act: 1.3909. Min Act: -0.0000

Data Index: 790507 (The Pile)

Max Activating Token Index: 249

Text #11

Max Range: 1.5989. Min Range: -1.5989

Max Act: 1.4022. Min Act: -0.0000

Data Index: 925431 (The Pile)

Max Activating Token Index: 79

Text #12

Max Range: 1.5989. Min Range: -1.5989

Max Act: 1.3123. Min Act: -0.0000

Data Index: 1809179 (The Pile)

Max Activating Token Index: 126

Text #13

Max Range: 1.5989. Min Range: -1.5989

Max Act: 1.3092. Min Act: -0.0000

Data Index: 1186326 (The Pile)

Max Activating Token Index: 688

Text #14

Max Range: 1.5989. Min Range: -1.5989

Max Act: 1.3960. Min Act: -0.0000

Data Index: 12110 (The Pile)

Max Activating Token Index: 1019

Text #15

Max Range: 1.5989. Min Range: -1.5989

Max Act: 1.2441. Min Act: -0.0000

Data Index: 1919538 (The Pile)

Max Activating Token Index: 109

Text #16

Max Range: 1.5989. Min Range: -1.5989

Max Act: 1.3110. Min Act: -0.0000

Data Index: 13266 (The Pile)

Max Activating Token Index: 710

Text #17

Max Range: 1.5989. Min Range: -1.5989

Max Act: 1.3544. Min Act: -0.0000

Data Index: 289670 (The Pile)

Max Activating Token Index: 688

Text #18

Max Range: 1.5989. Min Range: -1.5989

Max Act: 1.2539. Min Act: -0.0000

Data Index: 1885834 (The Pile)

Max Activating Token Index: 200

Text #19

Max Range: 1.5989. Min Range: -1.5989

Max Act: 1.3121. Min Act: -0.0000

Data Index: 892874 (The Pile)

Max Activating Token Index: 785