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

Dataset: The Pile

Neuron 3661 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: 0.6792. Min Range: -0.6792

Max Act: 0.6792. Min Act: -0.0000

Data Index: 651293 (The Pile)

Max Activating Token Index: 987

Text #1

Max Range: 0.6792. Min Range: -0.6792

Max Act: 0.5230. Min Act: -0.0000

Data Index: 244112 (The Pile)

Max Activating Token Index: 877

Text #2

Max Range: 0.6792. Min Range: -0.6792

Max Act: 0.5275. Min Act: -0.0000

Data Index: 1837776 (The Pile)

Max Activating Token Index: 818

Text #3

Max Range: 0.6792. Min Range: -0.6792

Max Act: 0.5895. Min Act: -0.0000

Data Index: 956091 (The Pile)

Max Activating Token Index: 35

Text #4

Max Range: 0.6792. Min Range: -0.6792

Max Act: 0.5451. Min Act: -0.0000

Data Index: 600015 (The Pile)

Max Activating Token Index: 519

Text #5

Max Range: 0.6792. Min Range: -0.6792

Max Act: 0.5544. Min Act: -0.0000

Data Index: 85060 (The Pile)

Max Activating Token Index: 488

Text #6

Max Range: 0.6792. Min Range: -0.6792

Max Act: 0.5274. Min Act: -0.0000

Data Index: 147020 (The Pile)

Max Activating Token Index: 114

Text #7

Max Range: 0.6792. Min Range: -0.6792

Max Act: 0.5459. Min Act: -0.0000

Data Index: 1906912 (The Pile)

Max Activating Token Index: 335

Text #8

Max Range: 0.6792. Min Range: -0.6792

Max Act: 0.5001. Min Act: -0.0000

Data Index: 506769 (The Pile)

Max Activating Token Index: 1006

Text #9

Max Range: 0.6792. Min Range: -0.6792

Max Act: 0.5340. Min Act: -0.0000

Data Index: 1961031 (The Pile)

Max Activating Token Index: 229

Text #10

Max Range: 0.6792. Min Range: -0.6792

Max Act: 0.5285. Min Act: -0.0000

Data Index: 382548 (The Pile)

Max Activating Token Index: 261

Text #11

Max Range: 0.6792. Min Range: -0.6792

Max Act: 0.5301. Min Act: -0.0000

Data Index: 1232734 (The Pile)

Max Activating Token Index: 714

Text #12

Max Range: 0.6792. Min Range: -0.6792

Max Act: 0.5122. Min Act: -0.0000

Data Index: 1650276 (The Pile)

Max Activating Token Index: 214

Text #13

Max Range: 0.6792. Min Range: -0.6792

Max Act: 0.4469. Min Act: -0.0000

Data Index: 478308 (The Pile)

Max Activating Token Index: 934

Text #14

Max Range: 0.6792. Min Range: -0.6792

Max Act: 0.5055. Min Act: -0.0000

Data Index: 726824 (The Pile)

Max Activating Token Index: 693

Text #15

Max Range: 0.6792. Min Range: -0.6792

Max Act: 0.4955. Min Act: -0.0000

Data Index: 1554120 (The Pile)

Max Activating Token Index: 708

Text #16

Max Range: 0.6792. Min Range: -0.6792

Max Act: 0.5049. Min Act: -0.0000

Data Index: 131855 (The Pile)

Max Activating Token Index: 237

Text #17

Max Range: 0.6792. Min Range: -0.6792

Max Act: 0.4839. Min Act: -0.0000

Data Index: 1634918 (The Pile)

Max Activating Token Index: 837

Text #18

Max Range: 0.6792. Min Range: -0.6792

Max Act: 0.4982. Min Act: -0.0000

Data Index: 949289 (The Pile)

Max Activating Token Index: 510

Text #19

Max Range: 0.6792. Min Range: -0.6792

Max Act: 0.4829. Min Act: -0.0000

Data Index: 565621 (The Pile)

Max Activating Token Index: 35