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

Dataset: The Pile

Neuron 1158 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: 1.5326. Min Range: -1.5326

Max Act: 1.5326. Min Act: -0.0000

Data Index: 1041146 (The Pile)

Max Activating Token Index: 383

Text #1

Max Range: 1.5326. Min Range: -1.5326

Max Act: 1.4149. Min Act: -0.0000

Data Index: 97041 (The Pile)

Max Activating Token Index: 167

Text #2

Max Range: 1.5326. Min Range: -1.5326

Max Act: 1.3760. Min Act: -0.0000

Data Index: 456552 (The Pile)

Max Activating Token Index: 397

Text #3

Max Range: 1.5326. Min Range: -1.5326

Max Act: 1.3774. Min Act: -0.0000

Data Index: 1140702 (The Pile)

Max Activating Token Index: 487

Text #4

Max Range: 1.5326. Min Range: -1.5326

Max Act: 1.3120. Min Act: -0.0000

Data Index: 1658903 (The Pile)

Max Activating Token Index: 40

Text #5

Max Range: 1.5326. Min Range: -1.5326

Max Act: 1.2888. Min Act: -0.0000

Data Index: 1258953 (The Pile)

Max Activating Token Index: 178

Text #6

Max Range: 1.5326. Min Range: -1.5326

Max Act: 1.3504. Min Act: -0.0000

Data Index: 210842 (The Pile)

Max Activating Token Index: 327

Text #7

Max Range: 1.5326. Min Range: -1.5326

Max Act: 1.2187. Min Act: -0.0000

Data Index: 1834478 (The Pile)

Max Activating Token Index: 515

Text #8

Max Range: 1.5326. Min Range: -1.5326

Max Act: 1.2161. Min Act: -0.0000

Data Index: 136338 (The Pile)

Max Activating Token Index: 178

Text #9

Max Range: 1.5326. Min Range: -1.5326

Max Act: 1.2388. Min Act: -0.0000

Data Index: 657631 (The Pile)

Max Activating Token Index: 354

Text #10

Max Range: 1.5326. Min Range: -1.5326

Max Act: 1.1609. Min Act: -0.0000

Data Index: 88830 (The Pile)

Max Activating Token Index: 75

Text #11

Max Range: 1.5326. Min Range: -1.5326

Max Act: 1.2739. Min Act: -0.0000

Data Index: 324458 (The Pile)

Max Activating Token Index: 22

Text #12

Max Range: 1.5326. Min Range: -1.5326

Max Act: 1.2544. Min Act: -0.0000

Data Index: 1727003 (The Pile)

Max Activating Token Index: 568

Text #13

Max Range: 1.5326. Min Range: -1.5326

Max Act: 1.1781. Min Act: -0.0000

Data Index: 254551 (The Pile)

Max Activating Token Index: 380

Text #14

Max Range: 1.5326. Min Range: -1.5326

Max Act: 1.2192. Min Act: -0.0000

Data Index: 1672871 (The Pile)

Max Activating Token Index: 29

Text #15

Max Range: 1.5326. Min Range: -1.5326

Max Act: 1.1212. Min Act: -0.0000

Data Index: 1291732 (The Pile)

Max Activating Token Index: 675

Text #16

Max Range: 1.5326. Min Range: -1.5326

Max Act: 1.1304. Min Act: -0.0000

Data Index: 1364721 (The Pile)

Max Activating Token Index: 696

Text #17

Max Range: 1.5326. Min Range: -1.5326

Max Act: 1.1417. Min Act: -0.0000

Data Index: 205160 (The Pile)

Max Activating Token Index: 136

Text #18

Max Range: 1.5326. Min Range: -1.5326

Max Act: 1.1001. Min Act: -0.0000

Data Index: 108072 (The Pile)

Max Activating Token Index: 21

Text #19

Max Range: 1.5326. Min Range: -1.5326

Max Act: 1.1215. Min Act: -0.0000

Data Index: 1542698 (The Pile)

Max Activating Token Index: 559