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

Dataset: The Pile

Neuron 2366 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.9698. Min Range: -0.9698

Max Act: 0.9698. Min Act: -0.0000

Data Index: 1592103 (The Pile)

Max Activating Token Index: 393

Text #1

Max Range: 0.9698. Min Range: -0.9698

Max Act: 0.6736. Min Act: -0.0000

Data Index: 638336 (The Pile)

Max Activating Token Index: 916

Text #2

Max Range: 0.9698. Min Range: -0.9698

Max Act: 0.7973. Min Act: -0.0000

Data Index: 731028 (The Pile)

Max Activating Token Index: 738

Text #3

Max Range: 0.9698. Min Range: -0.9698

Max Act: 0.7020. Min Act: -0.0000

Data Index: 154518 (The Pile)

Max Activating Token Index: 446

Text #4

Max Range: 0.9698. Min Range: -0.9698

Max Act: 0.7471. Min Act: -0.0000

Data Index: 1942218 (The Pile)

Max Activating Token Index: 693

Text #5

Max Range: 0.9698. Min Range: -0.9698

Max Act: 0.6077. Min Act: -0.0000

Data Index: 517199 (The Pile)

Max Activating Token Index: 540

Text #6

Max Range: 0.9698. Min Range: -0.9698

Max Act: 0.5857. Min Act: -0.0000

Data Index: 928289 (The Pile)

Max Activating Token Index: 799

Text #7

Max Range: 0.9698. Min Range: -0.9698

Max Act: 0.4650. Min Act: -0.0000

Data Index: 414043 (The Pile)

Max Activating Token Index: 735

Text #8

Max Range: 0.9698. Min Range: -0.9698

Max Act: 0.5350. Min Act: -0.0000

Data Index: 258699 (The Pile)

Max Activating Token Index: 623

Text #9

Max Range: 0.9698. Min Range: -0.9698

Max Act: 0.5708. Min Act: -0.0000

Data Index: 1986723 (The Pile)

Max Activating Token Index: 660

Text #10

Max Range: 0.9698. Min Range: -0.9698

Max Act: 0.5541. Min Act: -0.0000

Data Index: 1034375 (The Pile)

Max Activating Token Index: 618

Text #11

Max Range: 0.9698. Min Range: -0.9698

Max Act: 0.5276. Min Act: -0.0000

Data Index: 444472 (The Pile)

Max Activating Token Index: 219

Text #12

Max Range: 0.9698. Min Range: -0.9698

Max Act: 0.5381. Min Act: -0.0000

Data Index: 1570779 (The Pile)

Max Activating Token Index: 491

Text #13

Max Range: 0.9698. Min Range: -0.9698

Max Act: 0.5468. Min Act: -0.0000

Data Index: 1449234 (The Pile)

Max Activating Token Index: 647

Text #14

Max Range: 0.9698. Min Range: -0.9698

Max Act: 0.5459. Min Act: -0.0000

Data Index: 161479 (The Pile)

Max Activating Token Index: 792

Text #15

Max Range: 0.9698. Min Range: -0.9698

Max Act: 0.7420. Min Act: -0.0000

Data Index: 902826 (The Pile)

Max Activating Token Index: 867

Text #16

Max Range: 0.9698. Min Range: -0.9698

Max Act: 0.5255. Min Act: -0.0000

Data Index: 1531715 (The Pile)

Max Activating Token Index: 972

Text #17

Max Range: 0.9698. Min Range: -0.9698

Max Act: 0.6178. Min Act: -0.0000

Data Index: 28411 (The Pile)

Max Activating Token Index: 967

Text #18

Max Range: 0.9698. Min Range: -0.9698

Max Act: 0.5232. Min Act: -0.0000

Data Index: 788669 (The Pile)

Max Activating Token Index: 409

Text #19

Max Range: 0.9698. Min Range: -0.9698

Max Act: 0.4481. Min Act: -0.0000

Data Index: 212214 (The Pile)

Max Activating Token Index: 731