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

Dataset: The Pile

Neuron 1766 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: 0.6672. Min Range: -0.6672

Max Act: 0.6672. Min Act: -0.0000

Data Index: 1361088 (The Pile)

Max Activating Token Index: 596

Text #1

Max Range: 0.6672. Min Range: -0.6672

Max Act: 0.6623. Min Act: -0.0000

Data Index: 733102 (The Pile)

Max Activating Token Index: 931

Text #2

Max Range: 0.6672. Min Range: -0.6672

Max Act: 0.6186. Min Act: -0.0000

Data Index: 163018 (The Pile)

Max Activating Token Index: 971

Text #3

Max Range: 0.6672. Min Range: -0.6672

Max Act: 0.6570. Min Act: -0.0000

Data Index: 1671288 (The Pile)

Max Activating Token Index: 115

Text #4

Max Range: 0.6672. Min Range: -0.6672

Max Act: 0.5685. Min Act: -0.0000

Data Index: 1466539 (The Pile)

Max Activating Token Index: 118

Text #5

Max Range: 0.6672. Min Range: -0.6672

Max Act: 0.5980. Min Act: -0.0000

Data Index: 1905755 (The Pile)

Max Activating Token Index: 1018

Text #6

Max Range: 0.6672. Min Range: -0.6672

Max Act: 0.5725. Min Act: -0.0000

Data Index: 1021060 (The Pile)

Max Activating Token Index: 365

Text #7

Max Range: 0.6672. Min Range: -0.6672

Max Act: 0.5642. Min Act: -0.0000

Data Index: 1687792 (The Pile)

Max Activating Token Index: 411

Text #8

Max Range: 0.6672. Min Range: -0.6672

Max Act: 0.5115. Min Act: -0.0000

Data Index: 741679 (The Pile)

Max Activating Token Index: 910

Text #9

Max Range: 0.6672. Min Range: -0.6672

Max Act: 0.4727. Min Act: -0.0000

Data Index: 101437 (The Pile)

Max Activating Token Index: 448

Text #10

Max Range: 0.6672. Min Range: -0.6672

Max Act: 0.5415. Min Act: -0.0000

Data Index: 604344 (The Pile)

Max Activating Token Index: 387

Text #11

Max Range: 0.6672. Min Range: -0.6672

Max Act: 0.5149. Min Act: -0.0000

Data Index: 1633120 (The Pile)

Max Activating Token Index: 333

Text #12

Max Range: 0.6672. Min Range: -0.6672

Max Act: 0.5053. Min Act: -0.0000

Data Index: 182629 (The Pile)

Max Activating Token Index: 533

Text #13

Max Range: 0.6672. Min Range: -0.6672

Max Act: 0.5161. Min Act: -0.0000

Data Index: 366602 (The Pile)

Max Activating Token Index: 836

Text #14

Max Range: 0.6672. Min Range: -0.6672

Max Act: 0.5264. Min Act: -0.0000

Data Index: 826006 (The Pile)

Max Activating Token Index: 982

Text #15

Max Range: 0.6672. Min Range: -0.6672

Max Act: 0.5298. Min Act: -0.0000

Data Index: 613522 (The Pile)

Max Activating Token Index: 478

Text #16

Max Range: 0.6672. Min Range: -0.6672

Max Act: 0.5378. Min Act: -0.0000

Data Index: 111501 (The Pile)

Max Activating Token Index: 830

Text #17

Max Range: 0.6672. Min Range: -0.6672

Max Act: 0.5357. Min Act: -0.0000

Data Index: 801371 (The Pile)

Max Activating Token Index: 801

Text #18

Max Range: 0.6672. Min Range: -0.6672

Max Act: 0.4588. Min Act: -0.0000

Data Index: 1615032 (The Pile)

Max Activating Token Index: 522

Text #19

Max Range: 0.6672. Min Range: -0.6672

Max Act: 0.5216. Min Act: -0.0000

Data Index: 486198 (The Pile)

Max Activating Token Index: 931