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

Dataset: The Pile

Neuron 1013 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: 0.9909. Min Range: -0.9909

Max Act: 0.9909. Min Act: -0.0000

Data Index: 163716 (The Pile)

Max Activating Token Index: 516

Text #1

Max Range: 0.9909. Min Range: -0.9909

Max Act: 0.9816. Min Act: -0.0000

Data Index: 1582169 (The Pile)

Max Activating Token Index: 783

Text #2

Max Range: 0.9909. Min Range: -0.9909

Max Act: 0.9529. Min Act: -0.0000

Data Index: 1377833 (The Pile)

Max Activating Token Index: 327

Text #3

Max Range: 0.9909. Min Range: -0.9909

Max Act: 0.9520. Min Act: -0.0000

Data Index: 1112798 (The Pile)

Max Activating Token Index: 376

Text #4

Max Range: 0.9909. Min Range: -0.9909

Max Act: 0.8570. Min Act: -0.0000

Data Index: 562108 (The Pile)

Max Activating Token Index: 504

Text #5

Max Range: 0.9909. Min Range: -0.9909

Max Act: 0.9193. Min Act: -0.0000

Data Index: 1925520 (The Pile)

Max Activating Token Index: 75

Text #6

Max Range: 0.9909. Min Range: -0.9909

Max Act: 0.9017. Min Act: -0.0000

Data Index: 327780 (The Pile)

Max Activating Token Index: 349

Text #7

Max Range: 0.9909. Min Range: -0.9909

Max Act: 0.8722. Min Act: -0.0000

Data Index: 898401 (The Pile)

Max Activating Token Index: 728

Text #8

Max Range: 0.9909. Min Range: -0.9909

Max Act: 0.8099. Min Act: -0.0000

Data Index: 1185750 (The Pile)

Max Activating Token Index: 535

Text #9

Max Range: 0.9909. Min Range: -0.9909

Max Act: 0.8980. Min Act: -0.0000

Data Index: 1655758 (The Pile)

Max Activating Token Index: 811

Text #10

Max Range: 0.9909. Min Range: -0.9909

Max Act: 0.8671. Min Act: -0.0000

Data Index: 1943612 (The Pile)

Max Activating Token Index: 706

Text #11

Max Range: 0.9909. Min Range: -0.9909

Max Act: 0.8498. Min Act: -0.0000

Data Index: 1695796 (The Pile)

Max Activating Token Index: 475

Text #12

Max Range: 0.9909. Min Range: -0.9909

Max Act: 0.8769. Min Act: -0.0000

Data Index: 162422 (The Pile)

Max Activating Token Index: 406

Text #13

Max Range: 0.9909. Min Range: -0.9909

Max Act: 0.7289. Min Act: -0.0000

Data Index: 1926181 (The Pile)

Max Activating Token Index: 854

Text #14

Max Range: 0.9909. Min Range: -0.9909

Max Act: 0.8166. Min Act: -0.0000

Data Index: 1563241 (The Pile)

Max Activating Token Index: 135

Text #15

Max Range: 0.9909. Min Range: -0.9909

Max Act: 0.7836. Min Act: -0.0000

Data Index: 1220811 (The Pile)

Max Activating Token Index: 433

Text #16

Max Range: 0.9909. Min Range: -0.9909

Max Act: 0.8946. Min Act: -0.0000

Data Index: 778005 (The Pile)

Max Activating Token Index: 917

Text #17

Max Range: 0.9909. Min Range: -0.9909

Max Act: 0.8653. Min Act: -0.0000

Data Index: 1556934 (The Pile)

Max Activating Token Index: 446

Text #18

Max Range: 0.9909. Min Range: -0.9909

Max Act: 0.8070. Min Act: -0.0000

Data Index: 1434177 (The Pile)

Max Activating Token Index: 228

Text #19

Max Range: 0.9909. Min Range: -0.9909

Max Act: 0.9072. Min Act: -0.0000

Data Index: 1894854 (The Pile)

Max Activating Token Index: 588