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

Dataset: The Pile

Neuron 2704 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: 1.6216. Min Range: -1.6216

Max Act: 1.6216. Min Act: -0.0000

Data Index: 1894670 (The Pile)

Max Activating Token Index: 754

Text #1

Max Range: 1.6216. Min Range: -1.6216

Max Act: 1.5675. Min Act: -0.0000

Data Index: 338117 (The Pile)

Max Activating Token Index: 868

Text #2

Max Range: 1.6216. Min Range: -1.6216

Max Act: 1.1788. Min Act: -0.0000

Data Index: 1826404 (The Pile)

Max Activating Token Index: 661

Text #3

Max Range: 1.6216. Min Range: -1.6216

Max Act: 1.1097. Min Act: -0.0000

Data Index: 1378399 (The Pile)

Max Activating Token Index: 501

Text #4

Max Range: 1.6216. Min Range: -1.6216

Max Act: 1.0789. Min Act: -0.0000

Data Index: 1583972 (The Pile)

Max Activating Token Index: 564

Text #5

Max Range: 1.6216. Min Range: -1.6216

Max Act: 1.1157. Min Act: -0.0000

Data Index: 1260040 (The Pile)

Max Activating Token Index: 488

Text #6

Max Range: 1.6216. Min Range: -1.6216

Max Act: 0.9229. Min Act: -0.0000

Data Index: 43854 (The Pile)

Max Activating Token Index: 813

Text #7

Max Range: 1.6216. Min Range: -1.6216

Max Act: 0.9402. Min Act: -0.0000

Data Index: 139696 (The Pile)

Max Activating Token Index: 387

Text #8

Max Range: 1.6216. Min Range: -1.6216

Max Act: 0.8667. Min Act: -0.0000

Data Index: 1899603 (The Pile)

Max Activating Token Index: 974

Text #9

Max Range: 1.6216. Min Range: -1.6216

Max Act: 0.8325. Min Act: -0.0000

Data Index: 240091 (The Pile)

Max Activating Token Index: 235

Text #10

Max Range: 1.6216. Min Range: -1.6216

Max Act: 0.8894. Min Act: -0.0000

Data Index: 1282305 (The Pile)

Max Activating Token Index: 66

Text #11

Max Range: 1.6216. Min Range: -1.6216

Max Act: 0.8525. Min Act: -0.0000

Data Index: 212594 (The Pile)

Max Activating Token Index: 990

Text #12

Max Range: 1.6216. Min Range: -1.6216

Max Act: 0.7742. Min Act: -0.0000

Data Index: 690779 (The Pile)

Max Activating Token Index: 428

Text #13

Max Range: 1.6216. Min Range: -1.6216

Max Act: 0.8144. Min Act: -0.0000

Data Index: 1988726 (The Pile)

Max Activating Token Index: 256

Text #14

Max Range: 1.6216. Min Range: -1.6216

Max Act: 0.8524. Min Act: -0.0000

Data Index: 919758 (The Pile)

Max Activating Token Index: 950

Text #15

Max Range: 1.6216. Min Range: -1.6216

Max Act: 0.8290. Min Act: -0.0000

Data Index: 287953 (The Pile)

Max Activating Token Index: 521

Text #16

Max Range: 1.6216. Min Range: -1.6216

Max Act: 0.7775. Min Act: -0.0000

Data Index: 686130 (The Pile)

Max Activating Token Index: 283

Text #17

Max Range: 1.6216. Min Range: -1.6216

Max Act: 0.7630. Min Act: -0.0000

Data Index: 918357 (The Pile)

Max Activating Token Index: 212

Text #18

Max Range: 1.6216. Min Range: -1.6216

Max Act: 0.7838. Min Act: -0.0000

Data Index: 431402 (The Pile)

Max Activating Token Index: 626

Text #19

Max Range: 1.6216. Min Range: -1.6216

Max Act: 0.7918. Min Act: -0.0000

Data Index: 1957803 (The Pile)

Max Activating Token Index: 38