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

Dataset: The Pile

Neuron 1082 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: 0.1213. Min Range: -0.1213

Max Act: 0.1202. Min Act: -0.0000

Data Index: 1221983 (The Pile)

Max Activating Token Index: 953

Text #1

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.1213. Min Act: -0.0000

Data Index: 1934131 (The Pile)

Max Activating Token Index: 505

Text #2

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.1066. Min Act: -0.0000

Data Index: 348391 (The Pile)

Max Activating Token Index: 226

Text #3

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.1155. Min Act: -0.0000

Data Index: 1942079 (The Pile)

Max Activating Token Index: 622

Text #4

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.1056. Min Act: -0.0000

Data Index: 141659 (The Pile)

Max Activating Token Index: 384

Text #5

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0996. Min Act: -0.0000

Data Index: 1915649 (The Pile)

Max Activating Token Index: 813

Text #6

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.1024. Min Act: -0.0000

Data Index: 1512642 (The Pile)

Max Activating Token Index: 726

Text #7

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.1025. Min Act: -0.0000

Data Index: 1707795 (The Pile)

Max Activating Token Index: 952

Text #8

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.1009. Min Act: -0.0000

Data Index: 340498 (The Pile)

Max Activating Token Index: 942

Text #9

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0954. Min Act: -0.0000

Data Index: 963068 (The Pile)

Max Activating Token Index: 232

Text #10

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0976. Min Act: -0.0000

Data Index: 1642538 (The Pile)

Max Activating Token Index: 878

Text #11

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0975. Min Act: -0.0000

Data Index: 1026287 (The Pile)

Max Activating Token Index: 855

Text #12

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0977. Min Act: -0.0000

Data Index: 419881 (The Pile)

Max Activating Token Index: 619

Text #13

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0910. Min Act: -0.0000

Data Index: 960413 (The Pile)

Max Activating Token Index: 938

Text #14

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0982. Min Act: -0.0000

Data Index: 620078 (The Pile)

Max Activating Token Index: 772

Text #15

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0947. Min Act: -0.0000

Data Index: 140500 (The Pile)

Max Activating Token Index: 566

Text #16

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0906. Min Act: -0.0000

Data Index: 1656362 (The Pile)

Max Activating Token Index: 449

Text #17

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0873. Min Act: -0.0000

Data Index: 663295 (The Pile)

Max Activating Token Index: 1022

Text #18

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0962. Min Act: -0.0000

Data Index: 532077 (The Pile)

Max Activating Token Index: 369

Text #19

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0886. Min Act: -0.0000

Data Index: 1419449 (The Pile)

Max Activating Token Index: 893