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

Dataset: The Pile

Neuron 1765 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: 6.0905. Min Range: -6.0905

Max Act: 6.0905. Min Act: -0.0000

Data Index: 264723 (The Pile)

Max Activating Token Index: 627

Text #1

Max Range: 6.0905. Min Range: -6.0905

Max Act: 5.1548. Min Act: -0.0000

Data Index: 837645 (The Pile)

Max Activating Token Index: 862

Text #2

Max Range: 6.0905. Min Range: -6.0905

Max Act: 5.6906. Min Act: -0.0000

Data Index: 212212 (The Pile)

Max Activating Token Index: 659

Text #3

Max Range: 6.0905. Min Range: -6.0905

Max Act: 5.0091. Min Act: -0.0000

Data Index: 99978 (The Pile)

Max Activating Token Index: 764

Text #4

Max Range: 6.0905. Min Range: -6.0905

Max Act: 5.4291. Min Act: -0.0000

Data Index: 505718 (The Pile)

Max Activating Token Index: 589

Text #5

Max Range: 6.0905. Min Range: -6.0905

Max Act: 5.5663. Min Act: -0.0000

Data Index: 135742 (The Pile)

Max Activating Token Index: 717

Text #6

Max Range: 6.0905. Min Range: -6.0905

Max Act: 5.2881. Min Act: -0.0000

Data Index: 1627599 (The Pile)

Max Activating Token Index: 860

Text #7

Max Range: 6.0905. Min Range: -6.0905

Max Act: 5.0629. Min Act: -0.0000

Data Index: 1050264 (The Pile)

Max Activating Token Index: 908

Text #8

Max Range: 6.0905. Min Range: -6.0905

Max Act: 5.1825. Min Act: -0.0000

Data Index: 1438752 (The Pile)

Max Activating Token Index: 86

Text #9

Max Range: 6.0905. Min Range: -6.0905

Max Act: 5.3836. Min Act: -0.0000

Data Index: 372741 (The Pile)

Max Activating Token Index: 503

Text #10

Max Range: 6.0905. Min Range: -6.0905

Max Act: 5.3036. Min Act: -0.0000

Data Index: 245049 (The Pile)

Max Activating Token Index: 967

Text #11

Max Range: 6.0905. Min Range: -6.0905

Max Act: 4.7068. Min Act: -0.0000

Data Index: 1740773 (The Pile)

Max Activating Token Index: 577

Text #12

Max Range: 6.0905. Min Range: -6.0905

Max Act: 5.2532. Min Act: -0.0000

Data Index: 1491207 (The Pile)

Max Activating Token Index: 772

Text #13

Max Range: 6.0905. Min Range: -6.0905

Max Act: 5.0170. Min Act: -0.0000

Data Index: 1508372 (The Pile)

Max Activating Token Index: 775

Text #14

Max Range: 6.0905. Min Range: -6.0905

Max Act: 5.0219. Min Act: -0.0000

Data Index: 1814548 (The Pile)

Max Activating Token Index: 419

Text #15

Max Range: 6.0905. Min Range: -6.0905

Max Act: 4.9880. Min Act: -0.0000

Data Index: 613999 (The Pile)

Max Activating Token Index: 565

Text #16

Max Range: 6.0905. Min Range: -6.0905

Max Act: 4.7872. Min Act: -0.0000

Data Index: 1279145 (The Pile)

Max Activating Token Index: 747

Text #17

Max Range: 6.0905. Min Range: -6.0905

Max Act: 5.5742. Min Act: -0.0000

Data Index: 727637 (The Pile)

Max Activating Token Index: 944

Text #18

Max Range: 6.0905. Min Range: -6.0905

Max Act: 4.9654. Min Act: -0.0000

Data Index: 734880 (The Pile)

Max Activating Token Index: 925

Text #19

Max Range: 6.0905. Min Range: -6.0905

Max Act: 4.9400. Min Act: -0.0000

Data Index: 1865559 (The Pile)

Max Activating Token Index: 954