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

Dataset: The Pile

Neuron 1570 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: 0.2323. Min Range: -0.2323

Max Act: 0.2323. Min Act: -0.0000

Data Index: 836377 (The Pile)

Max Activating Token Index: 251

Text #1

Max Range: 0.2323. Min Range: -0.2323

Max Act: 0.2292. Min Act: -0.0000

Data Index: 1424298 (The Pile)

Max Activating Token Index: 255

Text #2

Max Range: 0.2323. Min Range: -0.2323

Max Act: 0.2174. Min Act: -0.0000

Data Index: 597338 (The Pile)

Max Activating Token Index: 498

Text #3

Max Range: 0.2323. Min Range: -0.2323

Max Act: 0.2252. Min Act: -0.0000

Data Index: 1973224 (The Pile)

Max Activating Token Index: 16

Text #4

Max Range: 0.2323. Min Range: -0.2323

Max Act: 0.2146. Min Act: -0.0000

Data Index: 780363 (The Pile)

Max Activating Token Index: 9

Text #5

Max Range: 0.2323. Min Range: -0.2323

Max Act: 0.2160. Min Act: -0.0000

Data Index: 883605 (The Pile)

Max Activating Token Index: 508

Text #6

Max Range: 0.2323. Min Range: -0.2323

Max Act: 0.1994. Min Act: -0.0000

Data Index: 714690 (The Pile)

Max Activating Token Index: 405

Text #7

Max Range: 0.2323. Min Range: -0.2323

Max Act: 0.1885. Min Act: -0.0000

Data Index: 496623 (The Pile)

Max Activating Token Index: 620

Text #8

Max Range: 0.2323. Min Range: -0.2323

Max Act: 0.1954. Min Act: -0.0000

Data Index: 1286625 (The Pile)

Max Activating Token Index: 579

Text #9

Max Range: 0.2323. Min Range: -0.2323

Max Act: 0.1957. Min Act: -0.0000

Data Index: 1714278 (The Pile)

Max Activating Token Index: 122

Text #10

Max Range: 0.2323. Min Range: -0.2323

Max Act: 0.1842. Min Act: -0.0000

Data Index: 1076808 (The Pile)

Max Activating Token Index: 115

Text #11

Max Range: 0.2323. Min Range: -0.2323

Max Act: 0.1944. Min Act: -0.0000

Data Index: 226418 (The Pile)

Max Activating Token Index: 508

Text #12

Max Range: 0.2323. Min Range: -0.2323

Max Act: 0.2132. Min Act: -0.0000

Data Index: 1804346 (The Pile)

Max Activating Token Index: 928

Text #13

Max Range: 0.2323. Min Range: -0.2323

Max Act: 0.1954. Min Act: -0.0000

Data Index: 1814773 (The Pile)

Max Activating Token Index: 908

Text #14

Max Range: 0.2323. Min Range: -0.2323

Max Act: 0.1941. Min Act: -0.0000

Data Index: 868827 (The Pile)

Max Activating Token Index: 488

Text #15

Max Range: 0.2323. Min Range: -0.2323

Max Act: 0.1882. Min Act: -0.0000

Data Index: 58997 (The Pile)

Max Activating Token Index: 635

Text #16

Max Range: 0.2323. Min Range: -0.2323

Max Act: 0.1729. Min Act: -0.0000

Data Index: 542842 (The Pile)

Max Activating Token Index: 35

Text #17

Max Range: 0.2323. Min Range: -0.2323

Max Act: 0.1715. Min Act: -0.0000

Data Index: 518439 (The Pile)

Max Activating Token Index: 19

Text #18

Max Range: 0.2323. Min Range: -0.2323

Max Act: 0.1890. Min Act: -0.0000

Data Index: 1040516 (The Pile)

Max Activating Token Index: 884

Text #19

Max Range: 0.2323. Min Range: -0.2323

Max Act: 0.2042. Min Act: -0.0000

Data Index: 776955 (The Pile)

Max Activating Token Index: 11