Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 971 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 0.2501. Min Range: -0.2501

Max Act: 0.2501. Min Act: -0.0000

Data Index: 374159 (The Pile)

Max Activating Token Index: 884

Text #1

Max Range: 0.2501. Min Range: -0.2501

Max Act: 0.2164. Min Act: -0.0000

Data Index: 1211295 (The Pile)

Max Activating Token Index: 356

Text #2

Max Range: 0.2501. Min Range: -0.2501

Max Act: 0.2279. Min Act: -0.0000

Data Index: 1236624 (The Pile)

Max Activating Token Index: 766

Text #3

Max Range: 0.2501. Min Range: -0.2501

Max Act: 0.2156. Min Act: 0.0000

Data Index: 897472 (The Pile)

Max Activating Token Index: 497

Text #4

Max Range: 0.2501. Min Range: -0.2501

Max Act: 0.2167. Min Act: -0.0000

Data Index: 1709321 (The Pile)

Max Activating Token Index: 44

Text #5

Max Range: 0.2501. Min Range: -0.2501

Max Act: 0.2192. Min Act: -0.0000

Data Index: 1874041 (The Pile)

Max Activating Token Index: 403

Text #6

Max Range: 0.2501. Min Range: -0.2501

Max Act: 0.2215. Min Act: -0.0000

Data Index: 445443 (The Pile)

Max Activating Token Index: 111

Text #7

Max Range: 0.2501. Min Range: -0.2501

Max Act: 0.2018. Min Act: 0.0001

Data Index: 1651635 (The Pile)

Max Activating Token Index: 104

Text #8

Max Range: 0.2501. Min Range: -0.2501

Max Act: 0.2012. Min Act: -0.0000

Data Index: 461875 (The Pile)

Max Activating Token Index: 893

Text #9

Max Range: 0.2501. Min Range: -0.2501

Max Act: 0.2003. Min Act: -0.0000

Data Index: 1530437 (The Pile)

Max Activating Token Index: 256

Text #10

Max Range: 0.2501. Min Range: -0.2501

Max Act: 0.1933. Min Act: -0.0000

Data Index: 843723 (The Pile)

Max Activating Token Index: 397

Text #11

Max Range: 0.2501. Min Range: -0.2501

Max Act: 0.1994. Min Act: -0.0000

Data Index: 218071 (The Pile)

Max Activating Token Index: 408

Text #12

Max Range: 0.2501. Min Range: -0.2501

Max Act: 0.1974. Min Act: -0.0000

Data Index: 1230309 (The Pile)

Max Activating Token Index: 179

Text #13

Max Range: 0.2501. Min Range: -0.2501

Max Act: 0.1974. Min Act: -0.0000

Data Index: 300583 (The Pile)

Max Activating Token Index: 476

Text #14

Max Range: 0.2501. Min Range: -0.2501

Max Act: 0.1957. Min Act: -0.0000

Data Index: 110530 (The Pile)

Max Activating Token Index: 796

Text #15

Max Range: 0.2501. Min Range: -0.2501

Max Act: 0.1942. Min Act: 0.0000

Data Index: 1286879 (The Pile)

Max Activating Token Index: 57

Text #16

Max Range: 0.2501. Min Range: -0.2501

Max Act: 0.1812. Min Act: -0.0000

Data Index: 420444 (The Pile)

Max Activating Token Index: 484

Text #17

Max Range: 0.2501. Min Range: -0.2501

Max Act: 0.1932. Min Act: 0.0000

Data Index: 1952068 (The Pile)

Max Activating Token Index: 347

Text #18

Max Range: 0.2501. Min Range: -0.2501

Max Act: 0.1931. Min Act: -0.0000

Data Index: 225422 (The Pile)

Max Activating Token Index: 179

Text #19

Max Range: 0.2501. Min Range: -0.2501

Max Act: 0.1981. Min Act: -0.0000

Data Index: 1595630 (The Pile)

Max Activating Token Index: 604