Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2588 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.2309. Min Act: -0.0000

Data Index: 1685150 (The Pile)

Max Activating Token Index: 440

Text #1

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.2450. Min Act: -0.0000

Data Index: 1053546 (The Pile)

Max Activating Token Index: 880

Text #2

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.2232. Min Act: -0.0000

Data Index: 1449188 (The Pile)

Max Activating Token Index: 650

Text #3

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.2233. Min Act: -0.0000

Data Index: 1385126 (The Pile)

Max Activating Token Index: 786

Text #4

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.2221. Min Act: -0.0000

Data Index: 1263893 (The Pile)

Max Activating Token Index: 79

Text #5

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.2100. Min Act: -0.0000

Data Index: 1636668 (The Pile)

Max Activating Token Index: 978

Text #6

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.2172. Min Act: -0.0000

Data Index: 429179 (The Pile)

Max Activating Token Index: 918

Text #7

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.2094. Min Act: -0.0000

Data Index: 840073 (The Pile)

Max Activating Token Index: 807

Text #8

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.1988. Min Act: -0.0000

Data Index: 1400385 (The Pile)

Max Activating Token Index: 664

Text #9

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.2002. Min Act: -0.0000

Data Index: 125055 (The Pile)

Max Activating Token Index: 641

Text #10

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.2057. Min Act: -0.0000

Data Index: 110746 (The Pile)

Max Activating Token Index: 819

Text #11

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.1999. Min Act: -0.0000

Data Index: 1945214 (The Pile)

Max Activating Token Index: 490

Text #12

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.1832. Min Act: -0.0000

Data Index: 804157 (The Pile)

Max Activating Token Index: 360

Text #13

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.1966. Min Act: -0.0000

Data Index: 58259 (The Pile)

Max Activating Token Index: 753

Text #14

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.1992. Min Act: -0.0000

Data Index: 1824972 (The Pile)

Max Activating Token Index: 766

Text #15

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.1846. Min Act: -0.0000

Data Index: 1232619 (The Pile)

Max Activating Token Index: 404

Text #16

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.2002. Min Act: -0.0000

Data Index: 1011967 (The Pile)

Max Activating Token Index: 956

Text #17

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.1929. Min Act: -0.0000

Data Index: 560030 (The Pile)

Max Activating Token Index: 583

Text #18

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.1904. Min Act: -0.0000

Data Index: 463748 (The Pile)

Max Activating Token Index: 307

Text #19

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.1918. Min Act: -0.0000

Data Index: 841418 (The Pile)

Max Activating Token Index: 721