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

Dataset: The Pile

Neuron 2842 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: 0.9797. Min Range: -0.9797

Max Act: 0.9797. Min Act: -0.0000

Data Index: 1790209 (The Pile)

Max Activating Token Index: 346

Text #1

Max Range: 0.9797. Min Range: -0.9797

Max Act: 0.8752. Min Act: -0.0000

Data Index: 102553 (The Pile)

Max Activating Token Index: 241

Text #2

Max Range: 0.9797. Min Range: -0.9797

Max Act: 0.7775. Min Act: -0.0000

Data Index: 482561 (The Pile)

Max Activating Token Index: 125

Text #3

Max Range: 0.9797. Min Range: -0.9797

Max Act: 0.7759. Min Act: -0.0000

Data Index: 614705 (The Pile)

Max Activating Token Index: 334

Text #4

Max Range: 0.9797. Min Range: -0.9797

Max Act: 0.7258. Min Act: 0.0000

Data Index: 595038 (The Pile)

Max Activating Token Index: 701

Text #5

Max Range: 0.9797. Min Range: -0.9797

Max Act: 0.8415. Min Act: -0.0000

Data Index: 556942 (The Pile)

Max Activating Token Index: 76

Text #6

Max Range: 0.9797. Min Range: -0.9797

Max Act: 0.7580. Min Act: -0.0000

Data Index: 1708213 (The Pile)

Max Activating Token Index: 885

Text #7

Max Range: 0.9797. Min Range: -0.9797

Max Act: 0.7452. Min Act: 0.0000

Data Index: 910381 (The Pile)

Max Activating Token Index: 226

Text #8

Max Range: 0.9797. Min Range: -0.9797

Max Act: 0.7327. Min Act: -0.0000

Data Index: 803830 (The Pile)

Max Activating Token Index: 116

Text #9

Max Range: 0.9797. Min Range: -0.9797

Max Act: 0.7508. Min Act: -0.0000

Data Index: 640096 (The Pile)

Max Activating Token Index: 302

Text #10

Max Range: 0.9797. Min Range: -0.9797

Max Act: 0.7406. Min Act: -0.0000

Data Index: 91091 (The Pile)

Max Activating Token Index: 504

Text #11

Max Range: 0.9797. Min Range: -0.9797

Max Act: 0.7091. Min Act: -0.0000

Data Index: 426782 (The Pile)

Max Activating Token Index: 144

Text #12

Max Range: 0.9797. Min Range: -0.9797

Max Act: 0.7117. Min Act: -0.0000

Data Index: 944788 (The Pile)

Max Activating Token Index: 349

Text #13

Max Range: 0.9797. Min Range: -0.9797

Max Act: 0.7550. Min Act: -0.0000

Data Index: 1332800 (The Pile)

Max Activating Token Index: 58

Text #14

Max Range: 0.9797. Min Range: -0.9797

Max Act: 0.6827. Min Act: -0.0000

Data Index: 1932919 (The Pile)

Max Activating Token Index: 314

Text #15

Max Range: 0.9797. Min Range: -0.9797

Max Act: 0.7101. Min Act: -0.0000

Data Index: 1972898 (The Pile)

Max Activating Token Index: 286

Text #16

Max Range: 0.9797. Min Range: -0.9797

Max Act: 0.7174. Min Act: -0.0000

Data Index: 1890678 (The Pile)

Max Activating Token Index: 389

Text #17

Max Range: 0.9797. Min Range: -0.9797

Max Act: 0.6899. Min Act: -0.0000

Data Index: 407641 (The Pile)

Max Activating Token Index: 17

Text #18

Max Range: 0.9797. Min Range: -0.9797

Max Act: 0.6893. Min Act: 0.0000

Data Index: 1832047 (The Pile)

Max Activating Token Index: 850

Text #19

Max Range: 0.9797. Min Range: -0.9797

Max Act: 0.6734. Min Act: -0.0000

Data Index: 498610 (The Pile)

Max Activating Token Index: 78