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

Dataset: The Pile

Neuron 685 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4100. Min Range: -0.4100

Max Act: 0.4100. Min Act: -0.0000

Data Index: 1729728 (The Pile)

Max Activating Token Index: 348

Text #1

Max Range: 0.4100. Min Range: -0.4100

Max Act: 0.4032. Min Act: -0.0000

Data Index: 477578 (The Pile)

Max Activating Token Index: 729

Text #2

Max Range: 0.4100. Min Range: -0.4100

Max Act: 0.3957. Min Act: -0.0000

Data Index: 872460 (The Pile)

Max Activating Token Index: 38

Text #3

Max Range: 0.4100. Min Range: -0.4100

Max Act: 0.3528. Min Act: -0.0000

Data Index: 1200686 (The Pile)

Max Activating Token Index: 407

Text #4

Max Range: 0.4100. Min Range: -0.4100

Max Act: 0.3536. Min Act: -0.0000

Data Index: 363830 (The Pile)

Max Activating Token Index: 476

Text #5

Max Range: 0.4100. Min Range: -0.4100

Max Act: 0.3768. Min Act: -0.0000

Data Index: 1620566 (The Pile)

Max Activating Token Index: 593

Text #6

Max Range: 0.4100. Min Range: -0.4100

Max Act: 0.3155. Min Act: -0.0000

Data Index: 736469 (The Pile)

Max Activating Token Index: 930

Text #7

Max Range: 0.4100. Min Range: -0.4100

Max Act: 0.3843. Min Act: -0.0000

Data Index: 780829 (The Pile)

Max Activating Token Index: 46

Text #8

Max Range: 0.4100. Min Range: -0.4100

Max Act: 0.3587. Min Act: -0.0000

Data Index: 1890641 (The Pile)

Max Activating Token Index: 55

Text #9

Max Range: 0.4100. Min Range: -0.4100

Max Act: 0.3914. Min Act: -0.0000

Data Index: 37370 (The Pile)

Max Activating Token Index: 791

Text #10

Max Range: 0.4100. Min Range: -0.4100

Max Act: 0.3546. Min Act: -0.0000

Data Index: 661103 (The Pile)

Max Activating Token Index: 355

Text #11

Max Range: 0.4100. Min Range: -0.4100

Max Act: 0.3655. Min Act: -0.0000

Data Index: 1042946 (The Pile)

Max Activating Token Index: 230

Text #12

Max Range: 0.4100. Min Range: -0.4100

Max Act: 0.3538. Min Act: -0.0000

Data Index: 881505 (The Pile)

Max Activating Token Index: 486

Text #13

Max Range: 0.4100. Min Range: -0.4100

Max Act: 0.3659. Min Act: -0.0000

Data Index: 1583934 (The Pile)

Max Activating Token Index: 409

Text #14

Max Range: 0.4100. Min Range: -0.4100

Max Act: 0.3530. Min Act: -0.0000

Data Index: 47896 (The Pile)

Max Activating Token Index: 801

Text #15

Max Range: 0.4100. Min Range: -0.4100

Max Act: 0.3783. Min Act: -0.0000

Data Index: 1943746 (The Pile)

Max Activating Token Index: 622

Text #16

Max Range: 0.4100. Min Range: -0.4100

Max Act: 0.3776. Min Act: -0.0000

Data Index: 677405 (The Pile)

Max Activating Token Index: 51

Text #17

Max Range: 0.4100. Min Range: -0.4100

Max Act: 0.3761. Min Act: -0.0000

Data Index: 928058 (The Pile)

Max Activating Token Index: 905

Text #18

Max Range: 0.4100. Min Range: -0.4100

Max Act: 0.3611. Min Act: -0.0000

Data Index: 1448840 (The Pile)

Max Activating Token Index: 24

Text #19

Max Range: 0.4100. Min Range: -0.4100

Max Act: 0.3495. Min Act: -0.0000

Data Index: 836445 (The Pile)

Max Activating Token Index: 658