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

Dataset: The Pile

Neuron 2798 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: 1.1023. Min Range: -1.1023

Max Act: 1.1023. Min Act: -0.0000

Data Index: 1091719 (The Pile)

Max Activating Token Index: 748

Text #1

Max Range: 1.1023. Min Range: -1.1023

Max Act: 1.0299. Min Act: -0.0000

Data Index: 1032303 (The Pile)

Max Activating Token Index: 814

Text #2

Max Range: 1.1023. Min Range: -1.1023

Max Act: 1.0148. Min Act: -0.0000

Data Index: 1269803 (The Pile)

Max Activating Token Index: 204

Text #3

Max Range: 1.1023. Min Range: -1.1023

Max Act: 0.9985. Min Act: -0.0000

Data Index: 139966 (The Pile)

Max Activating Token Index: 256

Text #4

Max Range: 1.1023. Min Range: -1.1023

Max Act: 0.9194. Min Act: -0.0000

Data Index: 1863025 (The Pile)

Max Activating Token Index: 345

Text #5

Max Range: 1.1023. Min Range: -1.1023

Max Act: 0.8615. Min Act: -0.0000

Data Index: 1815412 (The Pile)

Max Activating Token Index: 163

Text #6

Max Range: 1.1023. Min Range: -1.1023

Max Act: 0.7919. Min Act: -0.0000

Data Index: 574638 (The Pile)

Max Activating Token Index: 528

Text #7

Max Range: 1.1023. Min Range: -1.1023

Max Act: 0.7417. Min Act: -0.0000

Data Index: 446542 (The Pile)

Max Activating Token Index: 795

Text #8

Max Range: 1.1023. Min Range: -1.1023

Max Act: 0.6657. Min Act: -0.0000

Data Index: 1168275 (The Pile)

Max Activating Token Index: 708

Text #9

Max Range: 1.1023. Min Range: -1.1023

Max Act: 0.7619. Min Act: -0.0000

Data Index: 332646 (The Pile)

Max Activating Token Index: 557

Text #10

Max Range: 1.1023. Min Range: -1.1023

Max Act: 0.7380. Min Act: -0.0000

Data Index: 1945605 (The Pile)

Max Activating Token Index: 81

Text #11

Max Range: 1.1023. Min Range: -1.1023

Max Act: 0.8036. Min Act: -0.0000

Data Index: 1537296 (The Pile)

Max Activating Token Index: 197

Text #12

Max Range: 1.1023. Min Range: -1.1023

Max Act: 0.7531. Min Act: -0.0000

Data Index: 998467 (The Pile)

Max Activating Token Index: 707

Text #13

Max Range: 1.1023. Min Range: -1.1023

Max Act: 0.7210. Min Act: -0.0000

Data Index: 235481 (The Pile)

Max Activating Token Index: 637

Text #14

Max Range: 1.1023. Min Range: -1.1023

Max Act: 0.7417. Min Act: -0.0000

Data Index: 1196567 (The Pile)

Max Activating Token Index: 891

Text #15

Max Range: 1.1023. Min Range: -1.1023

Max Act: 0.7137. Min Act: -0.0000

Data Index: 748358 (The Pile)

Max Activating Token Index: 1008

Text #16

Max Range: 1.1023. Min Range: -1.1023

Max Act: 0.6836. Min Act: -0.0000

Data Index: 1901858 (The Pile)

Max Activating Token Index: 555

Text #17

Max Range: 1.1023. Min Range: -1.1023

Max Act: 0.7161. Min Act: -0.0000

Data Index: 1774098 (The Pile)

Max Activating Token Index: 496

Text #18

Max Range: 1.1023. Min Range: -1.1023

Max Act: 0.6905. Min Act: -0.0000

Data Index: 1778255 (The Pile)

Max Activating Token Index: 571

Text #19

Max Range: 1.1023. Min Range: -1.1023

Max Act: 0.6991. Min Act: -0.0000

Data Index: 1740316 (The Pile)

Max Activating Token Index: 363