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

Dataset: The Pile

Neuron 3612 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: 0.4834. Min Range: -0.4834

Max Act: 0.4834. Min Act: -0.0000

Data Index: 1738518 (The Pile)

Max Activating Token Index: 161

Text #1

Max Range: 0.4834. Min Range: -0.4834

Max Act: 0.3120. Min Act: 0.0000

Data Index: 1168113 (The Pile)

Max Activating Token Index: 624

Text #2

Max Range: 0.4834. Min Range: -0.4834

Max Act: 0.2566. Min Act: -0.0000

Data Index: 608031 (The Pile)

Max Activating Token Index: 172

Text #3

Max Range: 0.4834. Min Range: -0.4834

Max Act: 0.2378. Min Act: -0.0000

Data Index: 1217834 (The Pile)

Max Activating Token Index: 943

Text #4

Max Range: 0.4834. Min Range: -0.4834

Max Act: 0.2449. Min Act: -0.0000

Data Index: 616246 (The Pile)

Max Activating Token Index: 459

Text #5

Max Range: 0.4834. Min Range: -0.4834

Max Act: 0.2272. Min Act: -0.0000

Data Index: 1264547 (The Pile)

Max Activating Token Index: 879

Text #6

Max Range: 0.4834. Min Range: -0.4834

Max Act: 0.2430. Min Act: -0.0000

Data Index: 1983343 (The Pile)

Max Activating Token Index: 806

Text #7

Max Range: 0.4834. Min Range: -0.4834

Max Act: 0.2323. Min Act: -0.0000

Data Index: 1661429 (The Pile)

Max Activating Token Index: 781

Text #8

Max Range: 0.4834. Min Range: -0.4834

Max Act: 0.2208. Min Act: -0.0000

Data Index: 58739 (The Pile)

Max Activating Token Index: 989

Text #9

Max Range: 0.4834. Min Range: -0.4834

Max Act: 0.2361. Min Act: -0.0000

Data Index: 223926 (The Pile)

Max Activating Token Index: 150

Text #10

Max Range: 0.4834. Min Range: -0.4834

Max Act: 0.2173. Min Act: -0.0000

Data Index: 1271082 (The Pile)

Max Activating Token Index: 116

Text #11

Max Range: 0.4834. Min Range: -0.4834

Max Act: 0.2169. Min Act: -0.0000

Data Index: 662528 (The Pile)

Max Activating Token Index: 485

Text #12

Max Range: 0.4834. Min Range: -0.4834

Max Act: 0.2108. Min Act: -0.0000

Data Index: 924344 (The Pile)

Max Activating Token Index: 583

Text #13

Max Range: 0.4834. Min Range: -0.4834

Max Act: 0.2075. Min Act: -0.0000

Data Index: 325347 (The Pile)

Max Activating Token Index: 712

Text #14

Max Range: 0.4834. Min Range: -0.4834

Max Act: 0.1835. Min Act: -0.0000

Data Index: 936373 (The Pile)

Max Activating Token Index: 492

Text #15

Max Range: 0.4834. Min Range: -0.4834

Max Act: 0.2100. Min Act: -0.0000

Data Index: 1603578 (The Pile)

Max Activating Token Index: 538

Text #16

Max Range: 0.4834. Min Range: -0.4834

Max Act: 0.2033. Min Act: -0.0000

Data Index: 524925 (The Pile)

Max Activating Token Index: 165

Text #17

Max Range: 0.4834. Min Range: -0.4834

Max Act: 0.1929. Min Act: -0.0000

Data Index: 62460 (The Pile)

Max Activating Token Index: 57

Text #18

Max Range: 0.4834. Min Range: -0.4834

Max Act: 0.1905. Min Act: -0.0000

Data Index: 616372 (The Pile)

Max Activating Token Index: 122

Text #19

Max Range: 0.4834. Min Range: -0.4834

Max Act: 0.2119. Min Act: -0.0000

Data Index: 658660 (The Pile)

Max Activating Token Index: 505