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

Dataset: The Pile

Neuron 77 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1558. Min Range: -0.1558

Max Act: 0.1558. Min Act: -0.0000

Data Index: 978535 (The Pile)

Max Activating Token Index: 236

Text #1

Max Range: 0.1558. Min Range: -0.1558

Max Act: 0.1293. Min Act: -0.0000

Data Index: 1062041 (The Pile)

Max Activating Token Index: 820

Text #2

Max Range: 0.1558. Min Range: -0.1558

Max Act: 0.1308. Min Act: -0.0000

Data Index: 690091 (The Pile)

Max Activating Token Index: 513

Text #3

Max Range: 0.1558. Min Range: -0.1558

Max Act: 0.1293. Min Act: -0.0000

Data Index: 1795027 (The Pile)

Max Activating Token Index: 975

Text #4

Max Range: 0.1558. Min Range: -0.1558

Max Act: 0.1270. Min Act: -0.0000

Data Index: 1690173 (The Pile)

Max Activating Token Index: 325

Text #5

Max Range: 0.1558. Min Range: -0.1558

Max Act: 0.1211. Min Act: -0.0000

Data Index: 870918 (The Pile)

Max Activating Token Index: 701

Text #6

Max Range: 0.1558. Min Range: -0.1558

Max Act: 0.1226. Min Act: -0.0000

Data Index: 1959502 (The Pile)

Max Activating Token Index: 977

Text #7

Max Range: 0.1558. Min Range: -0.1558

Max Act: 0.1144. Min Act: -0.0000

Data Index: 1591401 (The Pile)

Max Activating Token Index: 855

Text #8

Max Range: 0.1558. Min Range: -0.1558

Max Act: 0.1219. Min Act: -0.0000

Data Index: 1077053 (The Pile)

Max Activating Token Index: 446

Text #9

Max Range: 0.1558. Min Range: -0.1558

Max Act: 0.1190. Min Act: -0.0000

Data Index: 1184062 (The Pile)

Max Activating Token Index: 737

Text #10

Max Range: 0.1558. Min Range: -0.1558

Max Act: 0.1166. Min Act: -0.0000

Data Index: 860203 (The Pile)

Max Activating Token Index: 951

Text #11

Max Range: 0.1558. Min Range: -0.1558

Max Act: 0.1119. Min Act: -0.0000

Data Index: 674179 (The Pile)

Max Activating Token Index: 967

Text #12

Max Range: 0.1558. Min Range: -0.1558

Max Act: 0.1080. Min Act: -0.0000

Data Index: 1913271 (The Pile)

Max Activating Token Index: 199

Text #13

Max Range: 0.1558. Min Range: -0.1558

Max Act: 0.1201. Min Act: -0.0000

Data Index: 1518044 (The Pile)

Max Activating Token Index: 789

Text #14

Max Range: 0.1558. Min Range: -0.1558

Max Act: 0.1070. Min Act: -0.0000

Data Index: 1269219 (The Pile)

Max Activating Token Index: 94

Text #15

Max Range: 0.1558. Min Range: -0.1558

Max Act: 0.1073. Min Act: -0.0000

Data Index: 510047 (The Pile)

Max Activating Token Index: 815

Text #16

Max Range: 0.1558. Min Range: -0.1558

Max Act: 0.1028. Min Act: -0.0000

Data Index: 1972862 (The Pile)

Max Activating Token Index: 98

Text #17

Max Range: 0.1558. Min Range: -0.1558

Max Act: 0.0974. Min Act: -0.0000

Data Index: 229456 (The Pile)

Max Activating Token Index: 869

Text #18

Max Range: 0.1558. Min Range: -0.1558

Max Act: 0.1014. Min Act: -0.0000

Data Index: 1328455 (The Pile)

Max Activating Token Index: 769

Text #19

Max Range: 0.1558. Min Range: -0.1558

Max Act: 0.1024. Min Act: -0.0000

Data Index: 746691 (The Pile)

Max Activating Token Index: 664