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

Dataset: The Pile

Neuron 376 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 12.0827. Min Range: -12.0827

Max Act: 11.8939. Min Act: -0.0000

Data Index: 693477 (The Pile)

Max Activating Token Index: 527

Text #1

Max Range: 12.0827. Min Range: -12.0827

Max Act: 12.0827. Min Act: -0.0000

Data Index: 1897299 (The Pile)

Max Activating Token Index: 406

Text #2

Max Range: 12.0827. Min Range: -12.0827

Max Act: 11.8805. Min Act: -0.0000

Data Index: 1895041 (The Pile)

Max Activating Token Index: 504

Text #3

Max Range: 12.0827. Min Range: -12.0827

Max Act: 11.8981. Min Act: -0.0000

Data Index: 402296 (The Pile)

Max Activating Token Index: 374

Text #4

Max Range: 12.0827. Min Range: -12.0827

Max Act: 11.6213. Min Act: -0.0000

Data Index: 1766543 (The Pile)

Max Activating Token Index: 696

Text #5

Max Range: 12.0827. Min Range: -12.0827

Max Act: 11.3239. Min Act: -0.0000

Data Index: 1070646 (The Pile)

Max Activating Token Index: 654

Text #6

Max Range: 12.0827. Min Range: -12.0827

Max Act: 10.9572. Min Act: -0.0000

Data Index: 399949 (The Pile)

Max Activating Token Index: 662

Text #7

Max Range: 12.0827. Min Range: -12.0827

Max Act: 12.0047. Min Act: -0.0000

Data Index: 1233596 (The Pile)

Max Activating Token Index: 603

Text #8

Max Range: 12.0827. Min Range: -12.0827

Max Act: 11.2336. Min Act: -0.0000

Data Index: 1294261 (The Pile)

Max Activating Token Index: 535

Text #9

Max Range: 12.0827. Min Range: -12.0827

Max Act: 11.1612. Min Act: -0.0000

Data Index: 915066 (The Pile)

Max Activating Token Index: 234

Text #10

Max Range: 12.0827. Min Range: -12.0827

Max Act: 11.3941. Min Act: -0.0000

Data Index: 902892 (The Pile)

Max Activating Token Index: 371

Text #11

Max Range: 12.0827. Min Range: -12.0827

Max Act: 11.7040. Min Act: -0.0000

Data Index: 1815218 (The Pile)

Max Activating Token Index: 578

Text #12

Max Range: 12.0827. Min Range: -12.0827

Max Act: 10.9741. Min Act: -0.0000

Data Index: 1987481 (The Pile)

Max Activating Token Index: 184

Text #13

Max Range: 12.0827. Min Range: -12.0827

Max Act: 11.1873. Min Act: -0.0000

Data Index: 1039687 (The Pile)

Max Activating Token Index: 259

Text #14

Max Range: 12.0827. Min Range: -12.0827

Max Act: 11.3113. Min Act: -0.0000

Data Index: 446458 (The Pile)

Max Activating Token Index: 279

Text #15

Max Range: 12.0827. Min Range: -12.0827

Max Act: 10.9494. Min Act: -0.0000

Data Index: 5215 (The Pile)

Max Activating Token Index: 230

Text #16

Max Range: 12.0827. Min Range: -12.0827

Max Act: 11.0465. Min Act: -0.0000

Data Index: 1338970 (The Pile)

Max Activating Token Index: 573

Text #17

Max Range: 12.0827. Min Range: -12.0827

Max Act: 10.5385. Min Act: -0.0000

Data Index: 1389204 (The Pile)

Max Activating Token Index: 658

Text #18

Max Range: 12.0827. Min Range: -12.0827

Max Act: 10.7888. Min Act: -0.0000

Data Index: 794807 (The Pile)

Max Activating Token Index: 993

Text #19

Max Range: 12.0827. Min Range: -12.0827

Max Act: 10.6609. Min Act: -0.0000

Data Index: 68477 (The Pile)

Max Activating Token Index: 262