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

Dataset: The Pile

Neuron 1822 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2355. Min Range: -0.2355

Max Act: 0.2355. Min Act: -0.0000

Data Index: 1217738 (The Pile)

Max Activating Token Index: 840

Text #1

Max Range: 0.2355. Min Range: -0.2355

Max Act: 0.2351. Min Act: 0.0000

Data Index: 612884 (The Pile)

Max Activating Token Index: 499

Text #2

Max Range: 0.2355. Min Range: -0.2355

Max Act: 0.2206. Min Act: -0.0000

Data Index: 1602633 (The Pile)

Max Activating Token Index: 625

Text #3

Max Range: 0.2355. Min Range: -0.2355

Max Act: 0.2075. Min Act: -0.0000

Data Index: 1783437 (The Pile)

Max Activating Token Index: 490

Text #4

Max Range: 0.2355. Min Range: -0.2355

Max Act: 0.2123. Min Act: -0.0000

Data Index: 834868 (The Pile)

Max Activating Token Index: 891

Text #5

Max Range: 0.2355. Min Range: -0.2355

Max Act: 0.1982. Min Act: -0.0000

Data Index: 1285599 (The Pile)

Max Activating Token Index: 572

Text #6

Max Range: 0.2355. Min Range: -0.2355

Max Act: 0.2062. Min Act: -0.0000

Data Index: 1782415 (The Pile)

Max Activating Token Index: 497

Text #7

Max Range: 0.2355. Min Range: -0.2355

Max Act: 0.2015. Min Act: -0.0000

Data Index: 1574842 (The Pile)

Max Activating Token Index: 538

Text #8

Max Range: 0.2355. Min Range: -0.2355

Max Act: 0.2009. Min Act: -0.0000

Data Index: 1136716 (The Pile)

Max Activating Token Index: 321

Text #9

Max Range: 0.2355. Min Range: -0.2355

Max Act: 0.1951. Min Act: -0.0000

Data Index: 1652269 (The Pile)

Max Activating Token Index: 787

Text #10

Max Range: 0.2355. Min Range: -0.2355

Max Act: 0.1894. Min Act: -0.0000

Data Index: 1611707 (The Pile)

Max Activating Token Index: 228

Text #11

Max Range: 0.2355. Min Range: -0.2355

Max Act: 0.1890. Min Act: -0.0000

Data Index: 1150465 (The Pile)

Max Activating Token Index: 685

Text #12

Max Range: 0.2355. Min Range: -0.2355

Max Act: 0.1833. Min Act: -0.0000

Data Index: 1609477 (The Pile)

Max Activating Token Index: 701

Text #13

Max Range: 0.2355. Min Range: -0.2355

Max Act: 0.1847. Min Act: -0.0000

Data Index: 48202 (The Pile)

Max Activating Token Index: 672

Text #14

Max Range: 0.2355. Min Range: -0.2355

Max Act: 0.1810. Min Act: -0.0000

Data Index: 1485513 (The Pile)

Max Activating Token Index: 322

Text #15

Max Range: 0.2355. Min Range: -0.2355

Max Act: 0.1746. Min Act: -0.0000

Data Index: 1590130 (The Pile)

Max Activating Token Index: 169

Text #16

Max Range: 0.2355. Min Range: -0.2355

Max Act: 0.1777. Min Act: -0.0000

Data Index: 643173 (The Pile)

Max Activating Token Index: 938

Text #17

Max Range: 0.2355. Min Range: -0.2355

Max Act: 0.1904. Min Act: -0.0000

Data Index: 221115 (The Pile)

Max Activating Token Index: 499

Text #18

Max Range: 0.2355. Min Range: -0.2355

Max Act: 0.1760. Min Act: -0.0000

Data Index: 1347448 (The Pile)

Max Activating Token Index: 544

Text #19

Max Range: 0.2355. Min Range: -0.2355

Max Act: 0.1769. Min Act: -0.0000

Data Index: 229732 (The Pile)

Max Activating Token Index: 405