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

Dataset: The Pile

Neuron 3822 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3109. Min Range: -0.3109

Max Act: 0.3109. Min Act: -0.0000

Data Index: 170568 (The Pile)

Max Activating Token Index: 915

Text #1

Max Range: 0.3109. Min Range: -0.3109

Max Act: 0.2540. Min Act: -0.0000

Data Index: 1019820 (The Pile)

Max Activating Token Index: 137

Text #2

Max Range: 0.3109. Min Range: -0.3109

Max Act: 0.2447. Min Act: -0.0000

Data Index: 202635 (The Pile)

Max Activating Token Index: 766

Text #3

Max Range: 0.3109. Min Range: -0.3109

Max Act: 0.2368. Min Act: -0.0000

Data Index: 817656 (The Pile)

Max Activating Token Index: 341

Text #4

Max Range: 0.3109. Min Range: -0.3109

Max Act: 0.2329. Min Act: -0.0000

Data Index: 1894583 (The Pile)

Max Activating Token Index: 658

Text #5

Max Range: 0.3109. Min Range: -0.3109

Max Act: 0.2438. Min Act: -0.0000

Data Index: 1019115 (The Pile)

Max Activating Token Index: 620

Text #6

Max Range: 0.3109. Min Range: -0.3109

Max Act: 0.2329. Min Act: -0.0000

Data Index: 959129 (The Pile)

Max Activating Token Index: 326

Text #7

Max Range: 0.3109. Min Range: -0.3109

Max Act: 0.2336. Min Act: -0.0000

Data Index: 39328 (The Pile)

Max Activating Token Index: 494

Text #8

Max Range: 0.3109. Min Range: -0.3109

Max Act: 0.2116. Min Act: -0.0000

Data Index: 751442 (The Pile)

Max Activating Token Index: 754

Text #9

Max Range: 0.3109. Min Range: -0.3109

Max Act: 0.2071. Min Act: -0.0000

Data Index: 1066958 (The Pile)

Max Activating Token Index: 982

Text #10

Max Range: 0.3109. Min Range: -0.3109

Max Act: 0.1967. Min Act: -0.0000

Data Index: 772819 (The Pile)

Max Activating Token Index: 195

Text #11

Max Range: 0.3109. Min Range: -0.3109

Max Act: 0.2013. Min Act: -0.0000

Data Index: 1495812 (The Pile)

Max Activating Token Index: 290

Text #12

Max Range: 0.3109. Min Range: -0.3109

Max Act: 0.2208. Min Act: -0.0000

Data Index: 287862 (The Pile)

Max Activating Token Index: 860

Text #13

Max Range: 0.3109. Min Range: -0.3109

Max Act: 0.2086. Min Act: -0.0000

Data Index: 543306 (The Pile)

Max Activating Token Index: 592

Text #14

Max Range: 0.3109. Min Range: -0.3109

Max Act: 0.2011. Min Act: -0.0000

Data Index: 265405 (The Pile)

Max Activating Token Index: 386

Text #15

Max Range: 0.3109. Min Range: -0.3109

Max Act: 0.1989. Min Act: -0.0000

Data Index: 332246 (The Pile)

Max Activating Token Index: 477

Text #16

Max Range: 0.3109. Min Range: -0.3109

Max Act: 0.1962. Min Act: -0.0000

Data Index: 720259 (The Pile)

Max Activating Token Index: 147

Text #17

Max Range: 0.3109. Min Range: -0.3109

Max Act: 0.2043. Min Act: -0.0000

Data Index: 1550170 (The Pile)

Max Activating Token Index: 356

Text #18

Max Range: 0.3109. Min Range: -0.3109

Max Act: 0.1710. Min Act: -0.0000

Data Index: 1934359 (The Pile)

Max Activating Token Index: 661

Text #19

Max Range: 0.3109. Min Range: -0.3109

Max Act: 0.1926. Min Act: -0.0000

Data Index: 1624774 (The Pile)

Max Activating Token Index: 477