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

Dataset: The Pile

Neuron 3477 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: 1.7031. Min Range: -1.7031

Max Act: 1.7031. Min Act: -0.0000

Data Index: 730453 (The Pile)

Max Activating Token Index: 775

Text #1

Max Range: 1.7031. Min Range: -1.7031

Max Act: 1.3832. Min Act: -0.0000

Data Index: 162589 (The Pile)

Max Activating Token Index: 708

Text #2

Max Range: 1.7031. Min Range: -1.7031

Max Act: 1.3636. Min Act: -0.0000

Data Index: 129495 (The Pile)

Max Activating Token Index: 1012

Text #3

Max Range: 1.7031. Min Range: -1.7031

Max Act: 1.3492. Min Act: -0.0000

Data Index: 1754956 (The Pile)

Max Activating Token Index: 894

Text #4

Max Range: 1.7031. Min Range: -1.7031

Max Act: 1.0731. Min Act: -0.0000

Data Index: 1254057 (The Pile)

Max Activating Token Index: 419

Text #5

Max Range: 1.7031. Min Range: -1.7031

Max Act: 1.1276. Min Act: -0.0000

Data Index: 921210 (The Pile)

Max Activating Token Index: 726

Text #6

Max Range: 1.7031. Min Range: -1.7031

Max Act: 0.9935. Min Act: -0.0000

Data Index: 356234 (The Pile)

Max Activating Token Index: 879

Text #7

Max Range: 1.7031. Min Range: -1.7031

Max Act: 1.0306. Min Act: -0.0000

Data Index: 1530628 (The Pile)

Max Activating Token Index: 842

Text #8

Max Range: 1.7031. Min Range: -1.7031

Max Act: 0.9798. Min Act: -0.0000

Data Index: 701846 (The Pile)

Max Activating Token Index: 766

Text #9

Max Range: 1.7031. Min Range: -1.7031

Max Act: 1.0117. Min Act: -0.0000

Data Index: 1322212 (The Pile)

Max Activating Token Index: 896

Text #10

Max Range: 1.7031. Min Range: -1.7031

Max Act: 0.9290. Min Act: -0.0000

Data Index: 1151854 (The Pile)

Max Activating Token Index: 357

Text #11

Max Range: 1.7031. Min Range: -1.7031

Max Act: 0.9113. Min Act: -0.0000

Data Index: 1074646 (The Pile)

Max Activating Token Index: 365

Text #12

Max Range: 1.7031. Min Range: -1.7031

Max Act: 0.8884. Min Act: -0.0000

Data Index: 1809685 (The Pile)

Max Activating Token Index: 594

Text #13

Max Range: 1.7031. Min Range: -1.7031

Max Act: 0.8539. Min Act: -0.0000

Data Index: 1930465 (The Pile)

Max Activating Token Index: 60

Text #14

Max Range: 1.7031. Min Range: -1.7031

Max Act: 0.8374. Min Act: -0.0000

Data Index: 1054900 (The Pile)

Max Activating Token Index: 13

Text #15

Max Range: 1.7031. Min Range: -1.7031

Max Act: 0.8318. Min Act: -0.0000

Data Index: 1313518 (The Pile)

Max Activating Token Index: 568

Text #16

Max Range: 1.7031. Min Range: -1.7031

Max Act: 0.8212. Min Act: -0.0000

Data Index: 1493488 (The Pile)

Max Activating Token Index: 163

Text #17

Max Range: 1.7031. Min Range: -1.7031

Max Act: 0.8779. Min Act: -0.0000

Data Index: 826801 (The Pile)

Max Activating Token Index: 1020

Text #18

Max Range: 1.7031. Min Range: -1.7031

Max Act: 0.8260. Min Act: -0.0000

Data Index: 544072 (The Pile)

Max Activating Token Index: 221

Text #19

Max Range: 1.7031. Min Range: -1.7031

Max Act: 0.8524. Min Act: -0.0000

Data Index: 1987040 (The Pile)

Max Activating Token Index: 476