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

Dataset: The Pile

Neuron 528 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: 0.5069. Min Range: -0.5069

Max Act: 0.4822. Min Act: -0.0000

Data Index: 1117285 (The Pile)

Max Activating Token Index: 711

Text #1

Max Range: 0.5069. Min Range: -0.5069

Max Act: 0.5031. Min Act: -0.0000

Data Index: 862134 (The Pile)

Max Activating Token Index: 994

Text #2

Max Range: 0.5069. Min Range: -0.5069

Max Act: 0.4778. Min Act: -0.0000

Data Index: 438655 (The Pile)

Max Activating Token Index: 905

Text #3

Max Range: 0.5069. Min Range: -0.5069

Max Act: 0.5069. Min Act: -0.0000

Data Index: 1429445 (The Pile)

Max Activating Token Index: 830

Text #4

Max Range: 0.5069. Min Range: -0.5069

Max Act: 0.4747. Min Act: -0.0000

Data Index: 1299156 (The Pile)

Max Activating Token Index: 473

Text #5

Max Range: 0.5069. Min Range: -0.5069

Max Act: 0.4566. Min Act: -0.0000

Data Index: 777859 (The Pile)

Max Activating Token Index: 613

Text #6

Max Range: 0.5069. Min Range: -0.5069

Max Act: 0.4178. Min Act: -0.0000

Data Index: 1906313 (The Pile)

Max Activating Token Index: 744

Text #7

Max Range: 0.5069. Min Range: -0.5069

Max Act: 0.3957. Min Act: -0.0000

Data Index: 130166 (The Pile)

Max Activating Token Index: 598

Text #8

Max Range: 0.5069. Min Range: -0.5069

Max Act: 0.4111. Min Act: -0.0000

Data Index: 268758 (The Pile)

Max Activating Token Index: 605

Text #9

Max Range: 0.5069. Min Range: -0.5069

Max Act: 0.3799. Min Act: -0.0000

Data Index: 961371 (The Pile)

Max Activating Token Index: 989

Text #10

Max Range: 0.5069. Min Range: -0.5069

Max Act: 0.4015. Min Act: -0.0000

Data Index: 896491 (The Pile)

Max Activating Token Index: 927

Text #11

Max Range: 0.5069. Min Range: -0.5069

Max Act: 0.3722. Min Act: -0.0000

Data Index: 865045 (The Pile)

Max Activating Token Index: 989

Text #12

Max Range: 0.5069. Min Range: -0.5069

Max Act: 0.3797. Min Act: -0.0000

Data Index: 696810 (The Pile)

Max Activating Token Index: 395

Text #13

Max Range: 0.5069. Min Range: -0.5069

Max Act: 0.3845. Min Act: -0.0000

Data Index: 356641 (The Pile)

Max Activating Token Index: 641

Text #14

Max Range: 0.5069. Min Range: -0.5069

Max Act: 0.3853. Min Act: -0.0000

Data Index: 1345917 (The Pile)

Max Activating Token Index: 424

Text #15

Max Range: 0.5069. Min Range: -0.5069

Max Act: 0.3413. Min Act: -0.0000

Data Index: 1296721 (The Pile)

Max Activating Token Index: 683

Text #16

Max Range: 0.5069. Min Range: -0.5069

Max Act: 0.3543. Min Act: -0.0000

Data Index: 414194 (The Pile)

Max Activating Token Index: 366

Text #17

Max Range: 0.5069. Min Range: -0.5069

Max Act: 0.3440. Min Act: -0.0000

Data Index: 1813379 (The Pile)

Max Activating Token Index: 1015

Text #18

Max Range: 0.5069. Min Range: -0.5069

Max Act: 0.3342. Min Act: -0.0000

Data Index: 456241 (The Pile)

Max Activating Token Index: 734

Text #19

Max Range: 0.5069. Min Range: -0.5069

Max Act: 0.3476. Min Act: -0.0000

Data Index: 96742 (The Pile)

Max Activating Token Index: 239