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

Dataset: The Pile

Neuron 4196 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: 1.4427. Min Range: -1.4427

Max Act: 1.4427. Min Act: -0.0000

Data Index: 538454 (The Pile)

Max Activating Token Index: 723

Text #1

Max Range: 1.4427. Min Range: -1.4427

Max Act: 1.3947. Min Act: -0.0000

Data Index: 1621299 (The Pile)

Max Activating Token Index: 619

Text #2

Max Range: 1.4427. Min Range: -1.4427

Max Act: 1.3559. Min Act: -0.0000

Data Index: 344722 (The Pile)

Max Activating Token Index: 627

Text #3

Max Range: 1.4427. Min Range: -1.4427

Max Act: 1.3590. Min Act: -0.0000

Data Index: 802675 (The Pile)

Max Activating Token Index: 404

Text #4

Max Range: 1.4427. Min Range: -1.4427

Max Act: 1.3075. Min Act: -0.0000

Data Index: 59528 (The Pile)

Max Activating Token Index: 523

Text #5

Max Range: 1.4427. Min Range: -1.4427

Max Act: 1.2375. Min Act: -0.0000

Data Index: 1033831 (The Pile)

Max Activating Token Index: 406

Text #6

Max Range: 1.4427. Min Range: -1.4427

Max Act: 1.3696. Min Act: -0.0000

Data Index: 1801809 (The Pile)

Max Activating Token Index: 754

Text #7

Max Range: 1.4427. Min Range: -1.4427

Max Act: 1.2311. Min Act: -0.0000

Data Index: 1167335 (The Pile)

Max Activating Token Index: 707

Text #8

Max Range: 1.4427. Min Range: -1.4427

Max Act: 1.3723. Min Act: -0.0000

Data Index: 1791175 (The Pile)

Max Activating Token Index: 525

Text #9

Max Range: 1.4427. Min Range: -1.4427

Max Act: 1.2867. Min Act: -0.0000

Data Index: 1191986 (The Pile)

Max Activating Token Index: 219

Text #10

Max Range: 1.4427. Min Range: -1.4427

Max Act: 1.1953. Min Act: -0.0000

Data Index: 613514 (The Pile)

Max Activating Token Index: 806

Text #11

Max Range: 1.4427. Min Range: -1.4427

Max Act: 1.1502. Min Act: -0.0000

Data Index: 1753731 (The Pile)

Max Activating Token Index: 892

Text #12

Max Range: 1.4427. Min Range: -1.4427

Max Act: 1.2088. Min Act: -0.0000

Data Index: 127775 (The Pile)

Max Activating Token Index: 1001

Text #13

Max Range: 1.4427. Min Range: -1.4427

Max Act: 1.1452. Min Act: -0.0000

Data Index: 1007853 (The Pile)

Max Activating Token Index: 372

Text #14

Max Range: 1.4427. Min Range: -1.4427

Max Act: 1.1738. Min Act: -0.0000

Data Index: 675188 (The Pile)

Max Activating Token Index: 372

Text #15

Max Range: 1.4427. Min Range: -1.4427

Max Act: 1.1528. Min Act: -0.0000

Data Index: 75692 (The Pile)

Max Activating Token Index: 333

Text #16

Max Range: 1.4427. Min Range: -1.4427

Max Act: 1.1490. Min Act: -0.0000

Data Index: 583494 (The Pile)

Max Activating Token Index: 251

Text #17

Max Range: 1.4427. Min Range: -1.4427

Max Act: 0.9783. Min Act: -0.0000

Data Index: 978932 (The Pile)

Max Activating Token Index: 984

Text #18

Max Range: 1.4427. Min Range: -1.4427

Max Act: 1.1057. Min Act: -0.0000

Data Index: 1147614 (The Pile)

Max Activating Token Index: 218

Text #19

Max Range: 1.4427. Min Range: -1.4427

Max Act: 1.1289. Min Act: -0.0000

Data Index: 1577104 (The Pile)

Max Activating Token Index: 244