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

Dataset: The Pile

Neuron 3086 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: 0.6229. Min Range: -0.6229

Max Act: 0.5561. Min Act: -0.0000

Data Index: 1263471 (The Pile)

Max Activating Token Index: 863

Text #1

Max Range: 0.6229. Min Range: -0.6229

Max Act: 0.5611. Min Act: -0.0000

Data Index: 1012317 (The Pile)

Max Activating Token Index: 827

Text #2

Max Range: 0.6229. Min Range: -0.6229

Max Act: 0.5800. Min Act: -0.0000

Data Index: 229742 (The Pile)

Max Activating Token Index: 1008

Text #3

Max Range: 0.6229. Min Range: -0.6229

Max Act: 0.6191. Min Act: -0.0000

Data Index: 43568 (The Pile)

Max Activating Token Index: 919

Text #4

Max Range: 0.6229. Min Range: -0.6229

Max Act: 0.5555. Min Act: -0.0000

Data Index: 973081 (The Pile)

Max Activating Token Index: 542

Text #5

Max Range: 0.6229. Min Range: -0.6229

Max Act: 0.5507. Min Act: -0.0000

Data Index: 1713796 (The Pile)

Max Activating Token Index: 614

Text #6

Max Range: 0.6229. Min Range: -0.6229

Max Act: 0.6229. Min Act: -0.0000

Data Index: 501148 (The Pile)

Max Activating Token Index: 666

Text #7

Max Range: 0.6229. Min Range: -0.6229

Max Act: 0.5655. Min Act: -0.0000

Data Index: 858288 (The Pile)

Max Activating Token Index: 158

Text #8

Max Range: 0.6229. Min Range: -0.6229

Max Act: 0.5324. Min Act: -0.0000

Data Index: 1407073 (The Pile)

Max Activating Token Index: 421

Text #9

Max Range: 0.6229. Min Range: -0.6229

Max Act: 0.4212. Min Act: -0.0000

Data Index: 1995128 (The Pile)

Max Activating Token Index: 844

Text #10

Max Range: 0.6229. Min Range: -0.6229

Max Act: 0.5574. Min Act: -0.0000

Data Index: 1605575 (The Pile)

Max Activating Token Index: 415

Text #11

Max Range: 0.6229. Min Range: -0.6229

Max Act: 0.4574. Min Act: -0.0000

Data Index: 1667112 (The Pile)

Max Activating Token Index: 329

Text #12

Max Range: 0.6229. Min Range: -0.6229

Max Act: 0.5338. Min Act: -0.0000

Data Index: 926437 (The Pile)

Max Activating Token Index: 637

Text #13

Max Range: 0.6229. Min Range: -0.6229

Max Act: 0.4184. Min Act: -0.0000

Data Index: 1196459 (The Pile)

Max Activating Token Index: 823

Text #14

Max Range: 0.6229. Min Range: -0.6229

Max Act: 0.4769. Min Act: -0.0000

Data Index: 1892289 (The Pile)

Max Activating Token Index: 609

Text #15

Max Range: 0.6229. Min Range: -0.6229

Max Act: 0.4295. Min Act: -0.0000

Data Index: 437306 (The Pile)

Max Activating Token Index: 685

Text #16

Max Range: 0.6229. Min Range: -0.6229

Max Act: 0.4567. Min Act: -0.0000

Data Index: 1857611 (The Pile)

Max Activating Token Index: 533

Text #17

Max Range: 0.6229. Min Range: -0.6229

Max Act: 0.4368. Min Act: -0.0000

Data Index: 1794415 (The Pile)

Max Activating Token Index: 54

Text #18

Max Range: 0.6229. Min Range: -0.6229

Max Act: 0.5388. Min Act: -0.0000

Data Index: 1702094 (The Pile)

Max Activating Token Index: 659

Text #19

Max Range: 0.6229. Min Range: -0.6229

Max Act: 0.5038. Min Act: -0.0000

Data Index: 1459264 (The Pile)

Max Activating Token Index: 798