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

Dataset: The Pile

Neuron 3704 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: 0.1556. Min Range: -0.1556

Max Act: 0.1556. Min Act: -0.0000

Data Index: 1997571 (The Pile)

Max Activating Token Index: 454

Text #1

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1477. Min Act: -0.0000

Data Index: 837000 (The Pile)

Max Activating Token Index: 415

Text #2

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1431. Min Act: -0.0000

Data Index: 395871 (The Pile)

Max Activating Token Index: 416

Text #3

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1432. Min Act: -0.0000

Data Index: 933639 (The Pile)

Max Activating Token Index: 284

Text #4

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1279. Min Act: -0.0000

Data Index: 1947673 (The Pile)

Max Activating Token Index: 545

Text #5

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1318. Min Act: -0.0000

Data Index: 1002705 (The Pile)

Max Activating Token Index: 399

Text #6

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1258. Min Act: -0.0000

Data Index: 264949 (The Pile)

Max Activating Token Index: 878

Text #7

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1453. Min Act: -0.0000

Data Index: 1693697 (The Pile)

Max Activating Token Index: 656

Text #8

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1252. Min Act: -0.0000

Data Index: 1506519 (The Pile)

Max Activating Token Index: 133

Text #9

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1186. Min Act: -0.0000

Data Index: 1254994 (The Pile)

Max Activating Token Index: 948

Text #10

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1263. Min Act: -0.0000

Data Index: 891503 (The Pile)

Max Activating Token Index: 519

Text #11

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1355. Min Act: -0.0000

Data Index: 662474 (The Pile)

Max Activating Token Index: 821

Text #12

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1249. Min Act: -0.0000

Data Index: 1137379 (The Pile)

Max Activating Token Index: 912

Text #13

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1174. Min Act: -0.0000

Data Index: 976505 (The Pile)

Max Activating Token Index: 298

Text #14

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1186. Min Act: -0.0000

Data Index: 394238 (The Pile)

Max Activating Token Index: 590

Text #15

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1131. Min Act: -0.0000

Data Index: 247952 (The Pile)

Max Activating Token Index: 681

Text #16

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1257. Min Act: -0.0000

Data Index: 154851 (The Pile)

Max Activating Token Index: 691

Text #17

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1336. Min Act: -0.0000

Data Index: 1908292 (The Pile)

Max Activating Token Index: 591

Text #18

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1198. Min Act: -0.0000

Data Index: 1472878 (The Pile)

Max Activating Token Index: 790

Text #19

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1068. Min Act: -0.0000

Data Index: 1578393 (The Pile)

Max Activating Token Index: 613