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

Dataset: The Pile

Neuron 3129 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0850. Min Range: -1.0850

Max Act: 1.0850. Min Act: -0.0000

Data Index: 1548892 (The Pile)

Max Activating Token Index: 100

Text #1

Max Range: 1.0850. Min Range: -1.0850

Max Act: 0.9987. Min Act: 0.0000

Data Index: 770544 (The Pile)

Max Activating Token Index: 452

Text #2

Max Range: 1.0850. Min Range: -1.0850

Max Act: 0.9960. Min Act: -0.0000

Data Index: 988807 (The Pile)

Max Activating Token Index: 850

Text #3

Max Range: 1.0850. Min Range: -1.0850

Max Act: 0.9852. Min Act: -0.0000

Data Index: 7744 (The Pile)

Max Activating Token Index: 733

Text #4

Max Range: 1.0850. Min Range: -1.0850

Max Act: 0.9589. Min Act: -0.0000

Data Index: 847918 (The Pile)

Max Activating Token Index: 115

Text #5

Max Range: 1.0850. Min Range: -1.0850

Max Act: 0.9177. Min Act: -0.0000

Data Index: 610408 (The Pile)

Max Activating Token Index: 1018

Text #6

Max Range: 1.0850. Min Range: -1.0850

Max Act: 0.8497. Min Act: -0.0000

Data Index: 1535543 (The Pile)

Max Activating Token Index: 516

Text #7

Max Range: 1.0850. Min Range: -1.0850

Max Act: 0.9518. Min Act: -0.0000

Data Index: 776892 (The Pile)

Max Activating Token Index: 438

Text #8

Max Range: 1.0850. Min Range: -1.0850

Max Act: 0.8914. Min Act: -0.0000

Data Index: 449916 (The Pile)

Max Activating Token Index: 159

Text #9

Max Range: 1.0850. Min Range: -1.0850

Max Act: 0.9189. Min Act: -0.0000

Data Index: 188674 (The Pile)

Max Activating Token Index: 772

Text #10

Max Range: 1.0850. Min Range: -1.0850

Max Act: 0.8234. Min Act: -0.0000

Data Index: 689325 (The Pile)

Max Activating Token Index: 890

Text #11

Max Range: 1.0850. Min Range: -1.0850

Max Act: 0.8263. Min Act: -0.0000

Data Index: 1655343 (The Pile)

Max Activating Token Index: 963

Text #12

Max Range: 1.0850. Min Range: -1.0850

Max Act: 0.8143. Min Act: -0.0000

Data Index: 201874 (The Pile)

Max Activating Token Index: 949

Text #13

Max Range: 1.0850. Min Range: -1.0850

Max Act: 0.8075. Min Act: -0.0000

Data Index: 112238 (The Pile)

Max Activating Token Index: 457

Text #14

Max Range: 1.0850. Min Range: -1.0850

Max Act: 0.7606. Min Act: -0.0000

Data Index: 1796395 (The Pile)

Max Activating Token Index: 994

Text #15

Max Range: 1.0850. Min Range: -1.0850

Max Act: 0.8654. Min Act: -0.0000

Data Index: 265339 (The Pile)

Max Activating Token Index: 572

Text #16

Max Range: 1.0850. Min Range: -1.0850

Max Act: 0.7558. Min Act: -0.0000

Data Index: 79230 (The Pile)

Max Activating Token Index: 624

Text #17

Max Range: 1.0850. Min Range: -1.0850

Max Act: 0.7812. Min Act: -0.0000

Data Index: 1871602 (The Pile)

Max Activating Token Index: 330

Text #18

Max Range: 1.0850. Min Range: -1.0850

Max Act: 0.7782. Min Act: -0.0000

Data Index: 1005942 (The Pile)

Max Activating Token Index: 617

Text #19

Max Range: 1.0850. Min Range: -1.0850

Max Act: 0.7307. Min Act: -0.0000

Data Index: 515508 (The Pile)

Max Activating Token Index: 897