Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2029 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.3260. Min Range: -1.3260

Max Act: 1.3260. Min Act: -0.0000

Data Index: 1554230 (The Pile)

Max Activating Token Index: 60

Text #1

Max Range: 1.3260. Min Range: -1.3260

Max Act: 1.1072. Min Act: -0.0000

Data Index: 1592848 (The Pile)

Max Activating Token Index: 69

Text #2

Max Range: 1.3260. Min Range: -1.3260

Max Act: 1.1861. Min Act: -0.0000

Data Index: 561076 (The Pile)

Max Activating Token Index: 468

Text #3

Max Range: 1.3260. Min Range: -1.3260

Max Act: 0.9944. Min Act: -0.0000

Data Index: 289933 (The Pile)

Max Activating Token Index: 325

Text #4

Max Range: 1.3260. Min Range: -1.3260

Max Act: 1.0230. Min Act: -0.0000

Data Index: 929470 (The Pile)

Max Activating Token Index: 16

Text #5

Max Range: 1.3260. Min Range: -1.3260

Max Act: 1.0688. Min Act: -0.0000

Data Index: 578840 (The Pile)

Max Activating Token Index: 23

Text #6

Max Range: 1.3260. Min Range: -1.3260

Max Act: 0.9584. Min Act: -0.0000

Data Index: 1979585 (The Pile)

Max Activating Token Index: 383

Text #7

Max Range: 1.3260. Min Range: -1.3260

Max Act: 1.1459. Min Act: -0.0000

Data Index: 1874076 (The Pile)

Max Activating Token Index: 136

Text #8

Max Range: 1.3260. Min Range: -1.3260

Max Act: 0.9255. Min Act: -0.0000

Data Index: 1149215 (The Pile)

Max Activating Token Index: 776

Text #9

Max Range: 1.3260. Min Range: -1.3260

Max Act: 0.9803. Min Act: -0.0000

Data Index: 1817999 (The Pile)

Max Activating Token Index: 69

Text #10

Max Range: 1.3260. Min Range: -1.3260

Max Act: 1.0027. Min Act: -0.0000

Data Index: 45648 (The Pile)

Max Activating Token Index: 534

Text #11

Max Range: 1.3260. Min Range: -1.3260

Max Act: 0.9244. Min Act: -0.0000

Data Index: 608727 (The Pile)

Max Activating Token Index: 155

Text #12

Max Range: 1.3260. Min Range: -1.3260

Max Act: 0.9923. Min Act: -0.0000

Data Index: 667617 (The Pile)

Max Activating Token Index: 110

Text #13

Max Range: 1.3260. Min Range: -1.3260

Max Act: 0.9166. Min Act: -0.0000

Data Index: 392440 (The Pile)

Max Activating Token Index: 705

Text #14

Max Range: 1.3260. Min Range: -1.3260

Max Act: 0.9716. Min Act: -0.0000

Data Index: 955973 (The Pile)

Max Activating Token Index: 259

Text #15

Max Range: 1.3260. Min Range: -1.3260

Max Act: 0.8613. Min Act: -0.0000

Data Index: 1011520 (The Pile)

Max Activating Token Index: 272

Text #16

Max Range: 1.3260. Min Range: -1.3260

Max Act: 0.8594. Min Act: -0.0000

Data Index: 1816308 (The Pile)

Max Activating Token Index: 661

Text #17

Max Range: 1.3260. Min Range: -1.3260

Max Act: 0.9613. Min Act: -0.0000

Data Index: 1310714 (The Pile)

Max Activating Token Index: 385

Text #18

Max Range: 1.3260. Min Range: -1.3260

Max Act: 0.8778. Min Act: -0.0000

Data Index: 618587 (The Pile)

Max Activating Token Index: 535

Text #19

Max Range: 1.3260. Min Range: -1.3260

Max Act: 0.9815. Min Act: -0.0000

Data Index: 390013 (The Pile)

Max Activating Token Index: 359