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

Dataset: The Pile

Neuron 2664 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7708. Min Range: -3.7708

Max Act: 3.7302. Min Act: -0.0000

Data Index: 766620 (The Pile)

Max Activating Token Index: 562

Text #1

Max Range: 3.7708. Min Range: -3.7708

Max Act: 3.4650. Min Act: -0.0000

Data Index: 1835883 (The Pile)

Max Activating Token Index: 623

Text #2

Max Range: 3.7708. Min Range: -3.7708

Max Act: 3.7708. Min Act: -0.0000

Data Index: 792529 (The Pile)

Max Activating Token Index: 230

Text #3

Max Range: 3.7708. Min Range: -3.7708

Max Act: 3.2779. Min Act: -0.0000

Data Index: 1006837 (The Pile)

Max Activating Token Index: 545

Text #4

Max Range: 3.7708. Min Range: -3.7708

Max Act: 3.4414. Min Act: -0.0000

Data Index: 1964652 (The Pile)

Max Activating Token Index: 57

Text #5

Max Range: 3.7708. Min Range: -3.7708

Max Act: 3.2732. Min Act: -0.0000

Data Index: 785605 (The Pile)

Max Activating Token Index: 462

Text #6

Max Range: 3.7708. Min Range: -3.7708

Max Act: 3.2036. Min Act: -0.0000

Data Index: 69584 (The Pile)

Max Activating Token Index: 628

Text #7

Max Range: 3.7708. Min Range: -3.7708

Max Act: 2.7771. Min Act: -0.0000

Data Index: 142692 (The Pile)

Max Activating Token Index: 1011

Text #8

Max Range: 3.7708. Min Range: -3.7708

Max Act: 2.7520. Min Act: -0.0000

Data Index: 1748692 (The Pile)

Max Activating Token Index: 835

Text #9

Max Range: 3.7708. Min Range: -3.7708

Max Act: 2.9475. Min Act: -0.0000

Data Index: 555894 (The Pile)

Max Activating Token Index: 999

Text #10

Max Range: 3.7708. Min Range: -3.7708

Max Act: 2.9010. Min Act: -0.0000

Data Index: 1642954 (The Pile)

Max Activating Token Index: 831

Text #11

Max Range: 3.7708. Min Range: -3.7708

Max Act: 2.5036. Min Act: -0.0000

Data Index: 632941 (The Pile)

Max Activating Token Index: 238

Text #12

Max Range: 3.7708. Min Range: -3.7708

Max Act: 2.6395. Min Act: -0.0000

Data Index: 1362045 (The Pile)

Max Activating Token Index: 746

Text #13

Max Range: 3.7708. Min Range: -3.7708

Max Act: 2.5538. Min Act: -0.0000

Data Index: 680047 (The Pile)

Max Activating Token Index: 818

Text #14

Max Range: 3.7708. Min Range: -3.7708

Max Act: 2.0698. Min Act: -0.0000

Data Index: 71192 (The Pile)

Max Activating Token Index: 871

Text #15

Max Range: 3.7708. Min Range: -3.7708

Max Act: 2.5151. Min Act: -0.0000

Data Index: 557345 (The Pile)

Max Activating Token Index: 479

Text #16

Max Range: 3.7708. Min Range: -3.7708

Max Act: 2.4868. Min Act: -0.0000

Data Index: 1961228 (The Pile)

Max Activating Token Index: 314

Text #17

Max Range: 3.7708. Min Range: -3.7708

Max Act: 2.4159. Min Act: -0.0000

Data Index: 1146683 (The Pile)

Max Activating Token Index: 638

Text #18

Max Range: 3.7708. Min Range: -3.7708

Max Act: 2.3976. Min Act: -0.0000

Data Index: 1468761 (The Pile)

Max Activating Token Index: 400

Text #19

Max Range: 3.7708. Min Range: -3.7708

Max Act: 2.3614. Min Act: -0.0000

Data Index: 491637 (The Pile)

Max Activating Token Index: 200