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

Dataset: The Pile

Neuron 624 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: 0.2323. Min Range: -0.2323

Max Act: 0.2323. Min Act: -0.0000

Data Index: 499245 (The Pile)

Max Activating Token Index: 116

Text #1

Max Range: 0.2323. Min Range: -0.2323

Max Act: 0.2141. Min Act: -0.0000

Data Index: 1102044 (The Pile)

Max Activating Token Index: 898

Text #2

Max Range: 0.2323. Min Range: -0.2323

Max Act: 0.2100. Min Act: 0.0000

Data Index: 1262807 (The Pile)

Max Activating Token Index: 411

Text #3

Max Range: 0.2323. Min Range: -0.2323

Max Act: 0.2055. Min Act: -0.0000

Data Index: 39116 (The Pile)

Max Activating Token Index: 382

Text #4

Max Range: 0.2323. Min Range: -0.2323

Max Act: 0.2275. Min Act: -0.0000

Data Index: 1876817 (The Pile)

Max Activating Token Index: 405

Text #5

Max Range: 0.2323. Min Range: -0.2323

Max Act: 0.2252. Min Act: -0.0000

Data Index: 799202 (The Pile)

Max Activating Token Index: 838

Text #6

Max Range: 0.2323. Min Range: -0.2323

Max Act: 0.2215. Min Act: -0.0000

Data Index: 1446078 (The Pile)

Max Activating Token Index: 1007

Text #7

Max Range: 0.2323. Min Range: -0.2323

Max Act: 0.1939. Min Act: -0.0000

Data Index: 1227527 (The Pile)

Max Activating Token Index: 274

Text #8

Max Range: 0.2323. Min Range: -0.2323

Max Act: 0.1570. Min Act: -0.0000

Data Index: 1524209 (The Pile)

Max Activating Token Index: 678

Text #9

Max Range: 0.2323. Min Range: -0.2323

Max Act: 0.1977. Min Act: -0.0000

Data Index: 1392690 (The Pile)

Max Activating Token Index: 324

Text #10

Max Range: 0.2323. Min Range: -0.2323

Max Act: 0.1865. Min Act: 0.0000

Data Index: 1044462 (The Pile)

Max Activating Token Index: 656

Text #11

Max Range: 0.2323. Min Range: -0.2323

Max Act: 0.1860. Min Act: -0.0000

Data Index: 542485 (The Pile)

Max Activating Token Index: 995

Text #12

Max Range: 0.2323. Min Range: -0.2323

Max Act: 0.2014. Min Act: -0.0000

Data Index: 151937 (The Pile)

Max Activating Token Index: 874

Text #13

Max Range: 0.2323. Min Range: -0.2323

Max Act: 0.1912. Min Act: -0.0000

Data Index: 417164 (The Pile)

Max Activating Token Index: 129

Text #14

Max Range: 0.2323. Min Range: -0.2323

Max Act: 0.1804. Min Act: -0.0000

Data Index: 1139711 (The Pile)

Max Activating Token Index: 616

Text #15

Max Range: 0.2323. Min Range: -0.2323

Max Act: 0.1872. Min Act: 0.0001

Data Index: 69070 (The Pile)

Max Activating Token Index: 123

Text #16

Max Range: 0.2323. Min Range: -0.2323

Max Act: 0.1960. Min Act: -0.0000

Data Index: 229553 (The Pile)

Max Activating Token Index: 989

Text #17

Max Range: 0.2323. Min Range: -0.2323

Max Act: 0.1949. Min Act: -0.0000

Data Index: 1854314 (The Pile)

Max Activating Token Index: 337

Text #18

Max Range: 0.2323. Min Range: -0.2323

Max Act: 0.1911. Min Act: 0.0000

Data Index: 673862 (The Pile)

Max Activating Token Index: 666

Text #19

Max Range: 0.2323. Min Range: -0.2323

Max Act: 0.1890. Min Act: 0.0000

Data Index: 1784228 (The Pile)

Max Activating Token Index: 224