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

Dataset: The Pile

Neuron 1257 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: 3.7805. Min Range: -3.7805

Max Act: 3.5801. Min Act: -0.0000

Data Index: 1609028 (The Pile)

Max Activating Token Index: 309

Text #1

Max Range: 3.7805. Min Range: -3.7805

Max Act: 3.5603. Min Act: -0.0000

Data Index: 58164 (The Pile)

Max Activating Token Index: 633

Text #2

Max Range: 3.7805. Min Range: -3.7805

Max Act: 3.5422. Min Act: -0.0000

Data Index: 814019 (The Pile)

Max Activating Token Index: 109

Text #3

Max Range: 3.7805. Min Range: -3.7805

Max Act: 3.4693. Min Act: -0.0000

Data Index: 1096880 (The Pile)

Max Activating Token Index: 81

Text #4

Max Range: 3.7805. Min Range: -3.7805

Max Act: 3.5851. Min Act: -0.0000

Data Index: 104285 (The Pile)

Max Activating Token Index: 111

Text #5

Max Range: 3.7805. Min Range: -3.7805

Max Act: 3.7072. Min Act: -0.0000

Data Index: 1326661 (The Pile)

Max Activating Token Index: 473

Text #6

Max Range: 3.7805. Min Range: -3.7805

Max Act: 3.6455. Min Act: -0.0000

Data Index: 464279 (The Pile)

Max Activating Token Index: 83

Text #7

Max Range: 3.7805. Min Range: -3.7805

Max Act: 3.7805. Min Act: -0.0000

Data Index: 119131 (The Pile)

Max Activating Token Index: 85

Text #8

Max Range: 3.7805. Min Range: -3.7805

Max Act: 3.4080. Min Act: -0.0000

Data Index: 1324109 (The Pile)

Max Activating Token Index: 440

Text #9

Max Range: 3.7805. Min Range: -3.7805

Max Act: 3.2661. Min Act: -0.0000

Data Index: 856618 (The Pile)

Max Activating Token Index: 346

Text #10

Max Range: 3.7805. Min Range: -3.7805

Max Act: 3.0227. Min Act: -0.0000

Data Index: 1833320 (The Pile)

Max Activating Token Index: 659

Text #11

Max Range: 3.7805. Min Range: -3.7805

Max Act: 3.2122. Min Act: -0.0000

Data Index: 837069 (The Pile)

Max Activating Token Index: 651

Text #12

Max Range: 3.7805. Min Range: -3.7805

Max Act: 3.4699. Min Act: -0.0000

Data Index: 673518 (The Pile)

Max Activating Token Index: 843

Text #13

Max Range: 3.7805. Min Range: -3.7805

Max Act: 3.1500. Min Act: -0.0000

Data Index: 1876961 (The Pile)

Max Activating Token Index: 623

Text #14

Max Range: 3.7805. Min Range: -3.7805

Max Act: 3.2633. Min Act: -0.0000

Data Index: 1867470 (The Pile)

Max Activating Token Index: 251

Text #15

Max Range: 3.7805. Min Range: -3.7805

Max Act: 3.1197. Min Act: -0.0000

Data Index: 417587 (The Pile)

Max Activating Token Index: 378

Text #16

Max Range: 3.7805. Min Range: -3.7805

Max Act: 3.3847. Min Act: -0.0000

Data Index: 1585796 (The Pile)

Max Activating Token Index: 210

Text #17

Max Range: 3.7805. Min Range: -3.7805

Max Act: 3.2211. Min Act: -0.0000

Data Index: 950590 (The Pile)

Max Activating Token Index: 653

Text #18

Max Range: 3.7805. Min Range: -3.7805

Max Act: 3.1869. Min Act: -0.0000

Data Index: 229635 (The Pile)

Max Activating Token Index: 546

Text #19

Max Range: 3.7805. Min Range: -3.7805

Max Act: 3.3205. Min Act: -0.0000

Data Index: 374388 (The Pile)

Max Activating Token Index: 177