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

Dataset: The Pile

Neuron 3191 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1409. Min Range: -0.1409

Max Act: 0.1409. Min Act: -0.0000

Data Index: 1278072 (The Pile)

Max Activating Token Index: 197

Text #1

Max Range: 0.1409. Min Range: -0.1409

Max Act: 0.1108. Min Act: -0.0000

Data Index: 862592 (The Pile)

Max Activating Token Index: 961

Text #2

Max Range: 0.1409. Min Range: -0.1409

Max Act: 0.1050. Min Act: -0.0000

Data Index: 151952 (The Pile)

Max Activating Token Index: 417

Text #3

Max Range: 0.1409. Min Range: -0.1409

Max Act: 0.1055. Min Act: -0.0000

Data Index: 649724 (The Pile)

Max Activating Token Index: 269

Text #4

Max Range: 0.1409. Min Range: -0.1409

Max Act: 0.1022. Min Act: -0.0000

Data Index: 74119 (The Pile)

Max Activating Token Index: 717

Text #5

Max Range: 0.1409. Min Range: -0.1409

Max Act: 0.1005. Min Act: -0.0000

Data Index: 979589 (The Pile)

Max Activating Token Index: 547

Text #6

Max Range: 0.1409. Min Range: -0.1409

Max Act: 0.1067. Min Act: -0.0000

Data Index: 320210 (The Pile)

Max Activating Token Index: 755

Text #7

Max Range: 0.1409. Min Range: -0.1409

Max Act: 0.0856. Min Act: -0.0000

Data Index: 914087 (The Pile)

Max Activating Token Index: 113

Text #8

Max Range: 0.1409. Min Range: -0.1409

Max Act: 0.1014. Min Act: -0.0000

Data Index: 122598 (The Pile)

Max Activating Token Index: 987

Text #9

Max Range: 0.1409. Min Range: -0.1409

Max Act: 0.0961. Min Act: -0.0000

Data Index: 1241792 (The Pile)

Max Activating Token Index: 739

Text #10

Max Range: 0.1409. Min Range: -0.1409

Max Act: 0.0888. Min Act: -0.0000

Data Index: 1113976 (The Pile)

Max Activating Token Index: 566

Text #11

Max Range: 0.1409. Min Range: -0.1409

Max Act: 0.0868. Min Act: -0.0000

Data Index: 796355 (The Pile)

Max Activating Token Index: 819

Text #12

Max Range: 0.1409. Min Range: -0.1409

Max Act: 0.0981. Min Act: -0.0000

Data Index: 1769231 (The Pile)

Max Activating Token Index: 263

Text #13

Max Range: 0.1409. Min Range: -0.1409

Max Act: 0.1036. Min Act: -0.0000

Data Index: 507414 (The Pile)

Max Activating Token Index: 557

Text #14

Max Range: 0.1409. Min Range: -0.1409

Max Act: 0.0933. Min Act: -0.0000

Data Index: 1104276 (The Pile)

Max Activating Token Index: 606

Text #15

Max Range: 0.1409. Min Range: -0.1409

Max Act: 0.0959. Min Act: -0.0000

Data Index: 1122759 (The Pile)

Max Activating Token Index: 321

Text #16

Max Range: 0.1409. Min Range: -0.1409

Max Act: 0.0991. Min Act: -0.0000

Data Index: 416787 (The Pile)

Max Activating Token Index: 605

Text #17

Max Range: 0.1409. Min Range: -0.1409

Max Act: 0.0881. Min Act: -0.0000

Data Index: 627437 (The Pile)

Max Activating Token Index: 406

Text #18

Max Range: 0.1409. Min Range: -0.1409

Max Act: 0.0965. Min Act: -0.0000

Data Index: 1366615 (The Pile)

Max Activating Token Index: 694

Text #19

Max Range: 0.1409. Min Range: -0.1409

Max Act: 0.0798. Min Act: -0.0000

Data Index: 1839507 (The Pile)

Max Activating Token Index: 731