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

Dataset: The Pile

Neuron 649 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: 1.0528. Min Range: -1.0528

Max Act: 1.0528. Min Act: -0.0000

Data Index: 1069140 (The Pile)

Max Activating Token Index: 220

Text #1

Max Range: 1.0528. Min Range: -1.0528

Max Act: 0.9260. Min Act: -0.0000

Data Index: 324427 (The Pile)

Max Activating Token Index: 998

Text #2

Max Range: 1.0528. Min Range: -1.0528

Max Act: 1.0115. Min Act: -0.0000

Data Index: 596783 (The Pile)

Max Activating Token Index: 480

Text #3

Max Range: 1.0528. Min Range: -1.0528

Max Act: 0.9994. Min Act: -0.0000

Data Index: 1074436 (The Pile)

Max Activating Token Index: 576

Text #4

Max Range: 1.0528. Min Range: -1.0528

Max Act: 0.9271. Min Act: -0.0000

Data Index: 1118068 (The Pile)

Max Activating Token Index: 526

Text #5

Max Range: 1.0528. Min Range: -1.0528

Max Act: 0.8563. Min Act: -0.0000

Data Index: 906895 (The Pile)

Max Activating Token Index: 786

Text #6

Max Range: 1.0528. Min Range: -1.0528

Max Act: 0.8757. Min Act: -0.0000

Data Index: 1877915 (The Pile)

Max Activating Token Index: 943

Text #7

Max Range: 1.0528. Min Range: -1.0528

Max Act: 0.7711. Min Act: -0.0000

Data Index: 1451533 (The Pile)

Max Activating Token Index: 610

Text #8

Max Range: 1.0528. Min Range: -1.0528

Max Act: 0.7704. Min Act: -0.0000

Data Index: 1360231 (The Pile)

Max Activating Token Index: 289

Text #9

Max Range: 1.0528. Min Range: -1.0528

Max Act: 0.7640. Min Act: -0.0000

Data Index: 746126 (The Pile)

Max Activating Token Index: 306

Text #10

Max Range: 1.0528. Min Range: -1.0528

Max Act: 0.7402. Min Act: -0.0000

Data Index: 982560 (The Pile)

Max Activating Token Index: 181

Text #11

Max Range: 1.0528. Min Range: -1.0528

Max Act: 0.7835. Min Act: -0.0000

Data Index: 1289664 (The Pile)

Max Activating Token Index: 836

Text #12

Max Range: 1.0528. Min Range: -1.0528

Max Act: 0.7172. Min Act: -0.0000

Data Index: 350941 (The Pile)

Max Activating Token Index: 650

Text #13

Max Range: 1.0528. Min Range: -1.0528

Max Act: 0.7112. Min Act: -0.0000

Data Index: 400979 (The Pile)

Max Activating Token Index: 813

Text #14

Max Range: 1.0528. Min Range: -1.0528

Max Act: 0.7426. Min Act: -0.0000

Data Index: 141096 (The Pile)

Max Activating Token Index: 650

Text #15

Max Range: 1.0528. Min Range: -1.0528

Max Act: 0.7315. Min Act: -0.0000

Data Index: 125928 (The Pile)

Max Activating Token Index: 769

Text #16

Max Range: 1.0528. Min Range: -1.0528

Max Act: 0.6752. Min Act: -0.0000

Data Index: 1920107 (The Pile)

Max Activating Token Index: 734

Text #17

Max Range: 1.0528. Min Range: -1.0528

Max Act: 0.7770. Min Act: -0.0000

Data Index: 1685497 (The Pile)

Max Activating Token Index: 778

Text #18

Max Range: 1.0528. Min Range: -1.0528

Max Act: 0.7065. Min Act: -0.0000

Data Index: 1702194 (The Pile)

Max Activating Token Index: 608

Text #19

Max Range: 1.0528. Min Range: -1.0528

Max Act: 0.6769. Min Act: -0.0000

Data Index: 885922 (The Pile)

Max Activating Token Index: 336