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

Dataset: The Pile

Neuron 4869 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: 0.9765. Min Range: -0.9765

Max Act: 0.9765. Min Act: -0.0000

Data Index: 441031 (The Pile)

Max Activating Token Index: 817

Text #1

Max Range: 0.9765. Min Range: -0.9765

Max Act: 0.9544. Min Act: -0.0000

Data Index: 1215343 (The Pile)

Max Activating Token Index: 919

Text #2

Max Range: 0.9765. Min Range: -0.9765

Max Act: 0.7517. Min Act: -0.0000

Data Index: 942562 (The Pile)

Max Activating Token Index: 903

Text #3

Max Range: 0.9765. Min Range: -0.9765

Max Act: 0.7755. Min Act: -0.0000

Data Index: 1205930 (The Pile)

Max Activating Token Index: 987

Text #4

Max Range: 0.9765. Min Range: -0.9765

Max Act: 0.6940. Min Act: -0.0000

Data Index: 1386459 (The Pile)

Max Activating Token Index: 174

Text #5

Max Range: 0.9765. Min Range: -0.9765

Max Act: 0.7254. Min Act: -0.0000

Data Index: 1075930 (The Pile)

Max Activating Token Index: 959

Text #6

Max Range: 0.9765. Min Range: -0.9765

Max Act: 0.7430. Min Act: -0.0000

Data Index: 294173 (The Pile)

Max Activating Token Index: 752

Text #7

Max Range: 0.9765. Min Range: -0.9765

Max Act: 0.6798. Min Act: -0.0000

Data Index: 1543816 (The Pile)

Max Activating Token Index: 307

Text #8

Max Range: 0.9765. Min Range: -0.9765

Max Act: 0.7039. Min Act: -0.0000

Data Index: 184679 (The Pile)

Max Activating Token Index: 805

Text #9

Max Range: 0.9765. Min Range: -0.9765

Max Act: 0.7692. Min Act: -0.0000

Data Index: 591549 (The Pile)

Max Activating Token Index: 101

Text #10

Max Range: 0.9765. Min Range: -0.9765

Max Act: 0.6353. Min Act: -0.0000

Data Index: 1411803 (The Pile)

Max Activating Token Index: 654

Text #11

Max Range: 0.9765. Min Range: -0.9765

Max Act: 0.7104. Min Act: -0.0000

Data Index: 271729 (The Pile)

Max Activating Token Index: 907

Text #12

Max Range: 0.9765. Min Range: -0.9765

Max Act: 0.7142. Min Act: -0.0000

Data Index: 1232697 (The Pile)

Max Activating Token Index: 664

Text #13

Max Range: 0.9765. Min Range: -0.9765

Max Act: 0.6864. Min Act: -0.0000

Data Index: 227041 (The Pile)

Max Activating Token Index: 107

Text #14

Max Range: 0.9765. Min Range: -0.9765

Max Act: 0.6575. Min Act: -0.0000

Data Index: 1621965 (The Pile)

Max Activating Token Index: 752

Text #15

Max Range: 0.9765. Min Range: -0.9765

Max Act: 0.6452. Min Act: -0.0000

Data Index: 932787 (The Pile)

Max Activating Token Index: 496

Text #16

Max Range: 0.9765. Min Range: -0.9765

Max Act: 0.6458. Min Act: -0.0000

Data Index: 884579 (The Pile)

Max Activating Token Index: 619

Text #17

Max Range: 0.9765. Min Range: -0.9765

Max Act: 0.6332. Min Act: -0.0000

Data Index: 1301739 (The Pile)

Max Activating Token Index: 357

Text #18

Max Range: 0.9765. Min Range: -0.9765

Max Act: 0.6202. Min Act: -0.0000

Data Index: 1378642 (The Pile)

Max Activating Token Index: 229

Text #19

Max Range: 0.9765. Min Range: -0.9765

Max Act: 0.6094. Min Act: -0.0000

Data Index: 1857628 (The Pile)

Max Activating Token Index: 333