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

Dataset: The Pile

Neuron 989 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2492. Min Range: -0.2492

Max Act: 0.2492. Min Act: -0.0000

Data Index: 172657 (The Pile)

Max Activating Token Index: 679

Text #1

Max Range: 0.2492. Min Range: -0.2492

Max Act: 0.2329. Min Act: -0.0000

Data Index: 1820279 (The Pile)

Max Activating Token Index: 519

Text #2

Max Range: 0.2492. Min Range: -0.2492

Max Act: 0.2255. Min Act: -0.0000

Data Index: 1980671 (The Pile)

Max Activating Token Index: 263

Text #3

Max Range: 0.2492. Min Range: -0.2492

Max Act: 0.2383. Min Act: -0.0000

Data Index: 572075 (The Pile)

Max Activating Token Index: 100

Text #4

Max Range: 0.2492. Min Range: -0.2492

Max Act: 0.2474. Min Act: -0.0000

Data Index: 1888176 (The Pile)

Max Activating Token Index: 624

Text #5

Max Range: 0.2492. Min Range: -0.2492

Max Act: 0.2272. Min Act: -0.0000

Data Index: 1572987 (The Pile)

Max Activating Token Index: 1005

Text #6

Max Range: 0.2492. Min Range: -0.2492

Max Act: 0.2026. Min Act: -0.0000

Data Index: 1759490 (The Pile)

Max Activating Token Index: 843

Text #7

Max Range: 0.2492. Min Range: -0.2492

Max Act: 0.2203. Min Act: -0.0000

Data Index: 1128306 (The Pile)

Max Activating Token Index: 474

Text #8

Max Range: 0.2492. Min Range: -0.2492

Max Act: 0.2125. Min Act: -0.0000

Data Index: 1281292 (The Pile)

Max Activating Token Index: 519

Text #9

Max Range: 0.2492. Min Range: -0.2492

Max Act: 0.1987. Min Act: -0.0000

Data Index: 1676413 (The Pile)

Max Activating Token Index: 636

Text #10

Max Range: 0.2492. Min Range: -0.2492

Max Act: 0.2320. Min Act: -0.0000

Data Index: 344096 (The Pile)

Max Activating Token Index: 687

Text #11

Max Range: 0.2492. Min Range: -0.2492

Max Act: 0.1970. Min Act: -0.0000

Data Index: 1827463 (The Pile)

Max Activating Token Index: 184

Text #12

Max Range: 0.2492. Min Range: -0.2492

Max Act: 0.2097. Min Act: -0.0000

Data Index: 1834030 (The Pile)

Max Activating Token Index: 720

Text #13

Max Range: 0.2492. Min Range: -0.2492

Max Act: 0.1887. Min Act: -0.0000

Data Index: 564299 (The Pile)

Max Activating Token Index: 813

Text #14

Max Range: 0.2492. Min Range: -0.2492

Max Act: 0.1974. Min Act: -0.0000

Data Index: 855591 (The Pile)

Max Activating Token Index: 814

Text #15

Max Range: 0.2492. Min Range: -0.2492

Max Act: 0.1930. Min Act: -0.0000

Data Index: 424780 (The Pile)

Max Activating Token Index: 724

Text #16

Max Range: 0.2492. Min Range: -0.2492

Max Act: 0.2028. Min Act: -0.0000

Data Index: 268446 (The Pile)

Max Activating Token Index: 406

Text #17

Max Range: 0.2492. Min Range: -0.2492

Max Act: 0.1868. Min Act: -0.0000

Data Index: 1734591 (The Pile)

Max Activating Token Index: 446

Text #18

Max Range: 0.2492. Min Range: -0.2492

Max Act: 0.1837. Min Act: -0.0000

Data Index: 807115 (The Pile)

Max Activating Token Index: 108

Text #19

Max Range: 0.2492. Min Range: -0.2492

Max Act: 0.1854. Min Act: -0.0000

Data Index: 454365 (The Pile)

Max Activating Token Index: 814