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

Dataset: The Pile

Neuron 3974 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: 7.9915. Min Range: -7.9915

Max Act: 7.9915. Min Act: -0.0000

Data Index: 808439 (The Pile)

Max Activating Token Index: 623

Text #1

Max Range: 7.9915. Min Range: -7.9915

Max Act: 7.9484. Min Act: -0.0000

Data Index: 1670232 (The Pile)

Max Activating Token Index: 700

Text #2

Max Range: 7.9915. Min Range: -7.9915

Max Act: 7.7891. Min Act: -0.0000

Data Index: 1541555 (The Pile)

Max Activating Token Index: 799

Text #3

Max Range: 7.9915. Min Range: -7.9915

Max Act: 7.2190. Min Act: -0.0000

Data Index: 239076 (The Pile)

Max Activating Token Index: 511

Text #4

Max Range: 7.9915. Min Range: -7.9915

Max Act: 7.4525. Min Act: -0.0000

Data Index: 1584976 (The Pile)

Max Activating Token Index: 529

Text #5

Max Range: 7.9915. Min Range: -7.9915

Max Act: 7.9478. Min Act: -0.0000

Data Index: 530129 (The Pile)

Max Activating Token Index: 827

Text #6

Max Range: 7.9915. Min Range: -7.9915

Max Act: 7.6696. Min Act: -0.0000

Data Index: 273439 (The Pile)

Max Activating Token Index: 890

Text #7

Max Range: 7.9915. Min Range: -7.9915

Max Act: 7.4397. Min Act: -0.0000

Data Index: 155891 (The Pile)

Max Activating Token Index: 923

Text #8

Max Range: 7.9915. Min Range: -7.9915

Max Act: 7.6688. Min Act: -0.0000

Data Index: 1570921 (The Pile)

Max Activating Token Index: 625

Text #9

Max Range: 7.9915. Min Range: -7.9915

Max Act: 7.6218. Min Act: -0.0000

Data Index: 814884 (The Pile)

Max Activating Token Index: 790

Text #10

Max Range: 7.9915. Min Range: -7.9915

Max Act: 7.9845. Min Act: -0.0000

Data Index: 1004921 (The Pile)

Max Activating Token Index: 972

Text #11

Max Range: 7.9915. Min Range: -7.9915

Max Act: 7.4256. Min Act: -0.0000

Data Index: 1817485 (The Pile)

Max Activating Token Index: 787

Text #12

Max Range: 7.9915. Min Range: -7.9915

Max Act: 7.8165. Min Act: -0.0000

Data Index: 1551098 (The Pile)

Max Activating Token Index: 182

Text #13

Max Range: 7.9915. Min Range: -7.9915

Max Act: 6.8462. Min Act: -0.0000

Data Index: 402336 (The Pile)

Max Activating Token Index: 909

Text #14

Max Range: 7.9915. Min Range: -7.9915

Max Act: 7.7957. Min Act: -0.0000

Data Index: 366113 (The Pile)

Max Activating Token Index: 362

Text #15

Max Range: 7.9915. Min Range: -7.9915

Max Act: 7.6113. Min Act: -0.0000

Data Index: 847424 (The Pile)

Max Activating Token Index: 590

Text #16

Max Range: 7.9915. Min Range: -7.9915

Max Act: 7.0447. Min Act: -0.0000

Data Index: 1152739 (The Pile)

Max Activating Token Index: 874

Text #17

Max Range: 7.9915. Min Range: -7.9915

Max Act: 6.7441. Min Act: -0.0000

Data Index: 343787 (The Pile)

Max Activating Token Index: 750

Text #18

Max Range: 7.9915. Min Range: -7.9915

Max Act: 7.5221. Min Act: -0.0000

Data Index: 1525291 (The Pile)

Max Activating Token Index: 1017

Text #19

Max Range: 7.9915. Min Range: -7.9915

Max Act: 6.9098. Min Act: -0.0000

Data Index: 1620490 (The Pile)

Max Activating Token Index: 691