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

Dataset: The Pile

Neuron 1066 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: 3.9856. Min Range: -3.9856

Max Act: 3.9856. Min Act: -0.0000

Data Index: 1746842 (The Pile)

Max Activating Token Index: 491

Text #1

Max Range: 3.9856. Min Range: -3.9856

Max Act: 3.0349. Min Act: -0.0000

Data Index: 363903 (The Pile)

Max Activating Token Index: 686

Text #2

Max Range: 3.9856. Min Range: -3.9856

Max Act: 2.6413. Min Act: -0.0000

Data Index: 1251884 (The Pile)

Max Activating Token Index: 925

Text #3

Max Range: 3.9856. Min Range: -3.9856

Max Act: 2.7024. Min Act: -0.0000

Data Index: 172881 (The Pile)

Max Activating Token Index: 334

Text #4

Max Range: 3.9856. Min Range: -3.9856

Max Act: 2.5396. Min Act: -0.0000

Data Index: 357791 (The Pile)

Max Activating Token Index: 376

Text #5

Max Range: 3.9856. Min Range: -3.9856

Max Act: 2.5246. Min Act: -0.0000

Data Index: 1124382 (The Pile)

Max Activating Token Index: 78

Text #6

Max Range: 3.9856. Min Range: -3.9856

Max Act: 2.1996. Min Act: -0.0000

Data Index: 367415 (The Pile)

Max Activating Token Index: 955

Text #7

Max Range: 3.9856. Min Range: -3.9856

Max Act: 2.1858. Min Act: -0.0000

Data Index: 486983 (The Pile)

Max Activating Token Index: 256

Text #8

Max Range: 3.9856. Min Range: -3.9856

Max Act: 2.1133. Min Act: -0.0000

Data Index: 45602 (The Pile)

Max Activating Token Index: 889

Text #9

Max Range: 3.9856. Min Range: -3.9856

Max Act: 2.2113. Min Act: -0.0000

Data Index: 548730 (The Pile)

Max Activating Token Index: 922

Text #10

Max Range: 3.9856. Min Range: -3.9856

Max Act: 2.0554. Min Act: -0.0000

Data Index: 994385 (The Pile)

Max Activating Token Index: 232

Text #11

Max Range: 3.9856. Min Range: -3.9856

Max Act: 1.8531. Min Act: -0.0000

Data Index: 100463 (The Pile)

Max Activating Token Index: 657

Text #12

Max Range: 3.9856. Min Range: -3.9856

Max Act: 1.9105. Min Act: -0.0000

Data Index: 731333 (The Pile)

Max Activating Token Index: 682

Text #13

Max Range: 3.9856. Min Range: -3.9856

Max Act: 1.8848. Min Act: -0.0000

Data Index: 876846 (The Pile)

Max Activating Token Index: 698

Text #14

Max Range: 3.9856. Min Range: -3.9856

Max Act: 1.7845. Min Act: -0.0000

Data Index: 606703 (The Pile)

Max Activating Token Index: 623

Text #15

Max Range: 3.9856. Min Range: -3.9856

Max Act: 1.7114. Min Act: -0.0000

Data Index: 1550462 (The Pile)

Max Activating Token Index: 1002

Text #16

Max Range: 3.9856. Min Range: -3.9856

Max Act: 1.7048. Min Act: -0.0000

Data Index: 578989 (The Pile)

Max Activating Token Index: 837

Text #17

Max Range: 3.9856. Min Range: -3.9856

Max Act: 1.8097. Min Act: -0.0000

Data Index: 1760863 (The Pile)

Max Activating Token Index: 180

Text #18

Max Range: 3.9856. Min Range: -3.9856

Max Act: 1.7986. Min Act: -0.0000

Data Index: 668839 (The Pile)

Max Activating Token Index: 302

Text #19

Max Range: 3.9856. Min Range: -3.9856

Max Act: 1.7929. Min Act: -0.0000

Data Index: 1809317 (The Pile)

Max Activating Token Index: 207