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

Dataset: The Pile

Neuron 4526 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5860. Min Range: -0.5860

Max Act: 0.5860. Min Act: -0.0000

Data Index: 146272 (The Pile)

Max Activating Token Index: 648

Text #1

Max Range: 0.5860. Min Range: -0.5860

Max Act: 0.4435. Min Act: -0.0000

Data Index: 1166828 (The Pile)

Max Activating Token Index: 926

Text #2

Max Range: 0.5860. Min Range: -0.5860

Max Act: 0.4532. Min Act: -0.0000

Data Index: 398214 (The Pile)

Max Activating Token Index: 357

Text #3

Max Range: 0.5860. Min Range: -0.5860

Max Act: 0.3998. Min Act: -0.0000

Data Index: 908095 (The Pile)

Max Activating Token Index: 831

Text #4

Max Range: 0.5860. Min Range: -0.5860

Max Act: 0.4761. Min Act: -0.0000

Data Index: 1615710 (The Pile)

Max Activating Token Index: 261

Text #5

Max Range: 0.5860. Min Range: -0.5860

Max Act: 0.4230. Min Act: -0.0000

Data Index: 1602555 (The Pile)

Max Activating Token Index: 458

Text #6

Max Range: 0.5860. Min Range: -0.5860

Max Act: 0.4400. Min Act: -0.0000

Data Index: 200666 (The Pile)

Max Activating Token Index: 467

Text #7

Max Range: 0.5860. Min Range: -0.5860

Max Act: 0.4814. Min Act: -0.0000

Data Index: 644450 (The Pile)

Max Activating Token Index: 551

Text #8

Max Range: 0.5860. Min Range: -0.5860

Max Act: 0.4698. Min Act: -0.0000

Data Index: 573034 (The Pile)

Max Activating Token Index: 407

Text #9

Max Range: 0.5860. Min Range: -0.5860

Max Act: 0.4574. Min Act: -0.0000

Data Index: 638115 (The Pile)

Max Activating Token Index: 891

Text #10

Max Range: 0.5860. Min Range: -0.5860

Max Act: 0.3861. Min Act: -0.0000

Data Index: 1179381 (The Pile)

Max Activating Token Index: 321

Text #11

Max Range: 0.5860. Min Range: -0.5860

Max Act: 0.4410. Min Act: -0.0000

Data Index: 1651101 (The Pile)

Max Activating Token Index: 687

Text #12

Max Range: 0.5860. Min Range: -0.5860

Max Act: 0.4704. Min Act: -0.0000

Data Index: 367179 (The Pile)

Max Activating Token Index: 531

Text #13

Max Range: 0.5860. Min Range: -0.5860

Max Act: 0.3751. Min Act: -0.0000

Data Index: 59997 (The Pile)

Max Activating Token Index: 688

Text #14

Max Range: 0.5860. Min Range: -0.5860

Max Act: 0.4237. Min Act: -0.0000

Data Index: 895887 (The Pile)

Max Activating Token Index: 496

Text #15

Max Range: 0.5860. Min Range: -0.5860

Max Act: 0.4165. Min Act: -0.0000

Data Index: 1890318 (The Pile)

Max Activating Token Index: 602

Text #16

Max Range: 0.5860. Min Range: -0.5860

Max Act: 0.4785. Min Act: -0.0000

Data Index: 461559 (The Pile)

Max Activating Token Index: 511

Text #17

Max Range: 0.5860. Min Range: -0.5860

Max Act: 0.4139. Min Act: -0.0000

Data Index: 977280 (The Pile)

Max Activating Token Index: 511

Text #18

Max Range: 0.5860. Min Range: -0.5860

Max Act: 0.3617. Min Act: -0.0000

Data Index: 1807719 (The Pile)

Max Activating Token Index: 887

Text #19

Max Range: 0.5860. Min Range: -0.5860

Max Act: 0.3739. Min Act: -0.0000

Data Index: 1969396 (The Pile)

Max Activating Token Index: 683