Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2377 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.7919. Min Range: -0.7919

Max Act: 0.7919. Min Act: -0.0000

Data Index: 300722 (The Pile)

Max Activating Token Index: 4

Text #1

Max Range: 0.7919. Min Range: -0.7919

Max Act: 0.7014. Min Act: -0.0000

Data Index: 1939772 (The Pile)

Max Activating Token Index: 732

Text #2

Max Range: 0.7919. Min Range: -0.7919

Max Act: 0.6309. Min Act: -0.0000

Data Index: 1801891 (The Pile)

Max Activating Token Index: 730

Text #3

Max Range: 0.7919. Min Range: -0.7919

Max Act: 0.5670. Min Act: -0.0000

Data Index: 1711411 (The Pile)

Max Activating Token Index: 425

Text #4

Max Range: 0.7919. Min Range: -0.7919

Max Act: 0.6118. Min Act: -0.0000

Data Index: 1922012 (The Pile)

Max Activating Token Index: 406

Text #5

Max Range: 0.7919. Min Range: -0.7919

Max Act: 0.6444. Min Act: -0.0000

Data Index: 341985 (The Pile)

Max Activating Token Index: 766

Text #6

Max Range: 0.7919. Min Range: -0.7919

Max Act: 0.5530. Min Act: -0.0000

Data Index: 1972343 (The Pile)

Max Activating Token Index: 972

Text #7

Max Range: 0.7919. Min Range: -0.7919

Max Act: 0.5949. Min Act: -0.0000

Data Index: 976381 (The Pile)

Max Activating Token Index: 870

Text #8

Max Range: 0.7919. Min Range: -0.7919

Max Act: 0.5530. Min Act: -0.0000

Data Index: 1968847 (The Pile)

Max Activating Token Index: 972

Text #9

Max Range: 0.7919. Min Range: -0.7919

Max Act: 0.5365. Min Act: -0.0000

Data Index: 893846 (The Pile)

Max Activating Token Index: 830

Text #10

Max Range: 0.7919. Min Range: -0.7919

Max Act: 0.5974. Min Act: -0.0000

Data Index: 138616 (The Pile)

Max Activating Token Index: 474

Text #11

Max Range: 0.7919. Min Range: -0.7919

Max Act: 0.6645. Min Act: -0.0000

Data Index: 315346 (The Pile)

Max Activating Token Index: 995

Text #12

Max Range: 0.7919. Min Range: -0.7919

Max Act: 0.5906. Min Act: -0.0000

Data Index: 595462 (The Pile)

Max Activating Token Index: 1000

Text #13

Max Range: 0.7919. Min Range: -0.7919

Max Act: 0.5338. Min Act: -0.0000

Data Index: 59222 (The Pile)

Max Activating Token Index: 456

Text #14

Max Range: 0.7919. Min Range: -0.7919

Max Act: 0.5824. Min Act: -0.0000

Data Index: 994062 (The Pile)

Max Activating Token Index: 483

Text #15

Max Range: 0.7919. Min Range: -0.7919

Max Act: 0.4577. Min Act: -0.0000

Data Index: 463977 (The Pile)

Max Activating Token Index: 595

Text #16

Max Range: 0.7919. Min Range: -0.7919

Max Act: 0.5062. Min Act: -0.0000

Data Index: 924907 (The Pile)

Max Activating Token Index: 256

Text #17

Max Range: 0.7919. Min Range: -0.7919

Max Act: 0.5132. Min Act: -0.0000

Data Index: 736710 (The Pile)

Max Activating Token Index: 272

Text #18

Max Range: 0.7919. Min Range: -0.7919

Max Act: 0.5054. Min Act: -0.0000

Data Index: 847768 (The Pile)

Max Activating Token Index: 791

Text #19

Max Range: 0.7919. Min Range: -0.7919

Max Act: 0.5606. Min Act: -0.0000

Data Index: 236851 (The Pile)

Max Activating Token Index: 74