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

Dataset: The Pile

Neuron 1006 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.1673. Min Range: -4.1673

Max Act: 4.1673. Min Act: -0.0000

Data Index: 37437 (The Pile)

Max Activating Token Index: 801

Text #1

Max Range: 4.1673. Min Range: -4.1673

Max Act: 3.8024. Min Act: -0.0000

Data Index: 1910875 (The Pile)

Max Activating Token Index: 567

Text #2

Max Range: 4.1673. Min Range: -4.1673

Max Act: 3.0792. Min Act: -0.0000

Data Index: 1075956 (The Pile)

Max Activating Token Index: 247

Text #3

Max Range: 4.1673. Min Range: -4.1673

Max Act: 3.1652. Min Act: -0.0000

Data Index: 292206 (The Pile)

Max Activating Token Index: 737

Text #4

Max Range: 4.1673. Min Range: -4.1673

Max Act: 3.1542. Min Act: -0.0000

Data Index: 721033 (The Pile)

Max Activating Token Index: 186

Text #5

Max Range: 4.1673. Min Range: -4.1673

Max Act: 2.9865. Min Act: -0.0000

Data Index: 1429471 (The Pile)

Max Activating Token Index: 208

Text #6

Max Range: 4.1673. Min Range: -4.1673

Max Act: 2.9696. Min Act: -0.0000

Data Index: 100364 (The Pile)

Max Activating Token Index: 732

Text #7

Max Range: 4.1673. Min Range: -4.1673

Max Act: 2.5797. Min Act: -0.0000

Data Index: 1056570 (The Pile)

Max Activating Token Index: 1008

Text #8

Max Range: 4.1673. Min Range: -4.1673

Max Act: 2.5870. Min Act: -0.0000

Data Index: 1470353 (The Pile)

Max Activating Token Index: 1021

Text #9

Max Range: 4.1673. Min Range: -4.1673

Max Act: 2.7251. Min Act: -0.0000

Data Index: 717734 (The Pile)

Max Activating Token Index: 594

Text #10

Max Range: 4.1673. Min Range: -4.1673

Max Act: 2.6033. Min Act: -0.0000

Data Index: 515361 (The Pile)

Max Activating Token Index: 143

Text #11

Max Range: 4.1673. Min Range: -4.1673

Max Act: 2.4392. Min Act: -0.0000

Data Index: 1100766 (The Pile)

Max Activating Token Index: 813

Text #12

Max Range: 4.1673. Min Range: -4.1673

Max Act: 2.2844. Min Act: -0.0000

Data Index: 1077784 (The Pile)

Max Activating Token Index: 709

Text #13

Max Range: 4.1673. Min Range: -4.1673

Max Act: 2.4861. Min Act: -0.0000

Data Index: 1423885 (The Pile)

Max Activating Token Index: 420

Text #14

Max Range: 4.1673. Min Range: -4.1673

Max Act: 2.2708. Min Act: -0.0000

Data Index: 485276 (The Pile)

Max Activating Token Index: 635

Text #15

Max Range: 4.1673. Min Range: -4.1673

Max Act: 2.2794. Min Act: -0.0000

Data Index: 1402279 (The Pile)

Max Activating Token Index: 113

Text #16

Max Range: 4.1673. Min Range: -4.1673

Max Act: 2.1332. Min Act: -0.0000

Data Index: 1841730 (The Pile)

Max Activating Token Index: 413

Text #17

Max Range: 4.1673. Min Range: -4.1673

Max Act: 2.3387. Min Act: -0.0000

Data Index: 189699 (The Pile)

Max Activating Token Index: 586

Text #18

Max Range: 4.1673. Min Range: -4.1673

Max Act: 1.9658. Min Act: -0.0000

Data Index: 856950 (The Pile)

Max Activating Token Index: 968

Text #19

Max Range: 4.1673. Min Range: -4.1673

Max Act: 2.3192. Min Act: -0.0000

Data Index: 1567218 (The Pile)

Max Activating Token Index: 328