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

Dataset: The Pile

Neuron 4471 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: 1.0219. Min Range: -1.0219

Max Act: 1.0219. Min Act: 0.0000

Data Index: 368924 (The Pile)

Max Activating Token Index: 422

Text #1

Max Range: 1.0219. Min Range: -1.0219

Max Act: 0.9277. Min Act: -0.0000

Data Index: 905347 (The Pile)

Max Activating Token Index: 287

Text #2

Max Range: 1.0219. Min Range: -1.0219

Max Act: 0.8306. Min Act: -0.0000

Data Index: 78861 (The Pile)

Max Activating Token Index: 919

Text #3

Max Range: 1.0219. Min Range: -1.0219

Max Act: 0.8779. Min Act: -0.0000

Data Index: 1522147 (The Pile)

Max Activating Token Index: 754

Text #4

Max Range: 1.0219. Min Range: -1.0219

Max Act: 0.8300. Min Act: 0.0000

Data Index: 585877 (The Pile)

Max Activating Token Index: 636

Text #5

Max Range: 1.0219. Min Range: -1.0219

Max Act: 0.8507. Min Act: -0.0000

Data Index: 1902805 (The Pile)

Max Activating Token Index: 689

Text #6

Max Range: 1.0219. Min Range: -1.0219

Max Act: 0.8687. Min Act: -0.0000

Data Index: 1738335 (The Pile)

Max Activating Token Index: 841

Text #7

Max Range: 1.0219. Min Range: -1.0219

Max Act: 0.8239. Min Act: -0.0000

Data Index: 1421736 (The Pile)

Max Activating Token Index: 654

Text #8

Max Range: 1.0219. Min Range: -1.0219

Max Act: 0.8417. Min Act: -0.0000

Data Index: 745907 (The Pile)

Max Activating Token Index: 643

Text #9

Max Range: 1.0219. Min Range: -1.0219

Max Act: 0.8278. Min Act: -0.0000

Data Index: 980868 (The Pile)

Max Activating Token Index: 163

Text #10

Max Range: 1.0219. Min Range: -1.0219

Max Act: 0.7775. Min Act: -0.0000

Data Index: 530776 (The Pile)

Max Activating Token Index: 148

Text #11

Max Range: 1.0219. Min Range: -1.0219

Max Act: 0.8180. Min Act: -0.0000

Data Index: 240569 (The Pile)

Max Activating Token Index: 539

Text #12

Max Range: 1.0219. Min Range: -1.0219

Max Act: 0.8138. Min Act: -0.0000

Data Index: 1160283 (The Pile)

Max Activating Token Index: 487

Text #13

Max Range: 1.0219. Min Range: -1.0219

Max Act: 0.7596. Min Act: -0.0000

Data Index: 1535662 (The Pile)

Max Activating Token Index: 93

Text #14

Max Range: 1.0219. Min Range: -1.0219

Max Act: 0.7888. Min Act: -0.0000

Data Index: 1522760 (The Pile)

Max Activating Token Index: 421

Text #15

Max Range: 1.0219. Min Range: -1.0219

Max Act: 0.7856. Min Act: -0.0000

Data Index: 634105 (The Pile)

Max Activating Token Index: 821

Text #16

Max Range: 1.0219. Min Range: -1.0219

Max Act: 0.8147. Min Act: -0.0000

Data Index: 860077 (The Pile)

Max Activating Token Index: 584

Text #17

Max Range: 1.0219. Min Range: -1.0219

Max Act: 0.7396. Min Act: -0.0000

Data Index: 356122 (The Pile)

Max Activating Token Index: 616

Text #18

Max Range: 1.0219. Min Range: -1.0219

Max Act: 0.7649. Min Act: -0.0000

Data Index: 1058364 (The Pile)

Max Activating Token Index: 466

Text #19

Max Range: 1.0219. Min Range: -1.0219

Max Act: 0.7784. Min Act: 0.0001

Data Index: 698521 (The Pile)

Max Activating Token Index: 789