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

Dataset: The Pile

Neuron 3299 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: 1.1999. Min Range: -1.1999

Max Act: 1.1679. Min Act: -0.0000

Data Index: 518168 (The Pile)

Max Activating Token Index: 173

Text #1

Max Range: 1.1999. Min Range: -1.1999

Max Act: 1.1999. Min Act: -0.0000

Data Index: 1065306 (The Pile)

Max Activating Token Index: 833

Text #2

Max Range: 1.1999. Min Range: -1.1999

Max Act: 1.1245. Min Act: -0.0000

Data Index: 1088267 (The Pile)

Max Activating Token Index: 432

Text #3

Max Range: 1.1999. Min Range: -1.1999

Max Act: 1.0521. Min Act: -0.0000

Data Index: 1322575 (The Pile)

Max Activating Token Index: 321

Text #4

Max Range: 1.1999. Min Range: -1.1999

Max Act: 0.9783. Min Act: -0.0000

Data Index: 1710837 (The Pile)

Max Activating Token Index: 273

Text #5

Max Range: 1.1999. Min Range: -1.1999

Max Act: 0.8520. Min Act: -0.0000

Data Index: 1991970 (The Pile)

Max Activating Token Index: 746

Text #6

Max Range: 1.1999. Min Range: -1.1999

Max Act: 0.8249. Min Act: -0.0000

Data Index: 1558983 (The Pile)

Max Activating Token Index: 743

Text #7

Max Range: 1.1999. Min Range: -1.1999

Max Act: 0.9483. Min Act: -0.0000

Data Index: 464221 (The Pile)

Max Activating Token Index: 905

Text #8

Max Range: 1.1999. Min Range: -1.1999

Max Act: 0.9230. Min Act: -0.0000

Data Index: 584370 (The Pile)

Max Activating Token Index: 427

Text #9

Max Range: 1.1999. Min Range: -1.1999

Max Act: 0.9119. Min Act: -0.0000

Data Index: 717714 (The Pile)

Max Activating Token Index: 867

Text #10

Max Range: 1.1999. Min Range: -1.1999

Max Act: 0.8223. Min Act: -0.0000

Data Index: 1053665 (The Pile)

Max Activating Token Index: 844

Text #11

Max Range: 1.1999. Min Range: -1.1999

Max Act: 0.8276. Min Act: -0.0000

Data Index: 573478 (The Pile)

Max Activating Token Index: 416

Text #12

Max Range: 1.1999. Min Range: -1.1999

Max Act: 0.8257. Min Act: -0.0000

Data Index: 1758347 (The Pile)

Max Activating Token Index: 543

Text #13

Max Range: 1.1999. Min Range: -1.1999

Max Act: 0.8261. Min Act: -0.0000

Data Index: 29960 (The Pile)

Max Activating Token Index: 878

Text #14

Max Range: 1.1999. Min Range: -1.1999

Max Act: 0.7276. Min Act: -0.0000

Data Index: 873222 (The Pile)

Max Activating Token Index: 698

Text #15

Max Range: 1.1999. Min Range: -1.1999

Max Act: 0.7630. Min Act: -0.0000

Data Index: 1289053 (The Pile)

Max Activating Token Index: 425

Text #16

Max Range: 1.1999. Min Range: -1.1999

Max Act: 0.7795. Min Act: -0.0000

Data Index: 1136828 (The Pile)

Max Activating Token Index: 481

Text #17

Max Range: 1.1999. Min Range: -1.1999

Max Act: 0.7520. Min Act: -0.0000

Data Index: 872486 (The Pile)

Max Activating Token Index: 470

Text #18

Max Range: 1.1999. Min Range: -1.1999

Max Act: 0.6888. Min Act: -0.0000

Data Index: 1960684 (The Pile)

Max Activating Token Index: 670

Text #19

Max Range: 1.1999. Min Range: -1.1999

Max Act: 0.6834. Min Act: -0.0000

Data Index: 1404205 (The Pile)

Max Activating Token Index: 524