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

Dataset: The Pile

Neuron 1803 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.9270. Min Range: -0.9270

Max Act: 0.9270. Min Act: -0.0000

Data Index: 875169 (The Pile)

Max Activating Token Index: 245

Text #1

Max Range: 0.9270. Min Range: -0.9270

Max Act: 0.9026. Min Act: -0.0000

Data Index: 1500388 (The Pile)

Max Activating Token Index: 563

Text #2

Max Range: 0.9270. Min Range: -0.9270

Max Act: 0.7973. Min Act: -0.0000

Data Index: 1647996 (The Pile)

Max Activating Token Index: 591

Text #3

Max Range: 0.9270. Min Range: -0.9270

Max Act: 0.7710. Min Act: -0.0000

Data Index: 1671817 (The Pile)

Max Activating Token Index: 895

Text #4

Max Range: 0.9270. Min Range: -0.9270

Max Act: 0.8243. Min Act: -0.0000

Data Index: 1501493 (The Pile)

Max Activating Token Index: 685

Text #5

Max Range: 0.9270. Min Range: -0.9270

Max Act: 0.7328. Min Act: -0.0000

Data Index: 198996 (The Pile)

Max Activating Token Index: 712

Text #6

Max Range: 0.9270. Min Range: -0.9270

Max Act: 0.6711. Min Act: -0.0000

Data Index: 48291 (The Pile)

Max Activating Token Index: 809

Text #7

Max Range: 0.9270. Min Range: -0.9270

Max Act: 0.6654. Min Act: -0.0000

Data Index: 1407855 (The Pile)

Max Activating Token Index: 333

Text #8

Max Range: 0.9270. Min Range: -0.9270

Max Act: 0.7116. Min Act: -0.0000

Data Index: 855524 (The Pile)

Max Activating Token Index: 504

Text #9

Max Range: 0.9270. Min Range: -0.9270

Max Act: 0.5909. Min Act: -0.0000

Data Index: 1680753 (The Pile)

Max Activating Token Index: 744

Text #10

Max Range: 0.9270. Min Range: -0.9270

Max Act: 0.6109. Min Act: -0.0000

Data Index: 1638478 (The Pile)

Max Activating Token Index: 419

Text #11

Max Range: 0.9270. Min Range: -0.9270

Max Act: 0.6065. Min Act: -0.0000

Data Index: 808903 (The Pile)

Max Activating Token Index: 124

Text #12

Max Range: 0.9270. Min Range: -0.9270

Max Act: 0.5826. Min Act: -0.0000

Data Index: 1070822 (The Pile)

Max Activating Token Index: 730

Text #13

Max Range: 0.9270. Min Range: -0.9270

Max Act: 0.5873. Min Act: -0.0000

Data Index: 637451 (The Pile)

Max Activating Token Index: 174

Text #14

Max Range: 0.9270. Min Range: -0.9270

Max Act: 0.5543. Min Act: -0.0000

Data Index: 324119 (The Pile)

Max Activating Token Index: 642

Text #15

Max Range: 0.9270. Min Range: -0.9270

Max Act: 0.5817. Min Act: -0.0000

Data Index: 1335671 (The Pile)

Max Activating Token Index: 173

Text #16

Max Range: 0.9270. Min Range: -0.9270

Max Act: 0.5985. Min Act: -0.0000

Data Index: 216133 (The Pile)

Max Activating Token Index: 739

Text #17

Max Range: 0.9270. Min Range: -0.9270

Max Act: 0.5818. Min Act: -0.0000

Data Index: 1718580 (The Pile)

Max Activating Token Index: 527

Text #18

Max Range: 0.9270. Min Range: -0.9270

Max Act: 0.5515. Min Act: -0.0000

Data Index: 381181 (The Pile)

Max Activating Token Index: 373

Text #19

Max Range: 0.9270. Min Range: -0.9270

Max Act: 0.6031. Min Act: -0.0000

Data Index: 1546381 (The Pile)

Max Activating Token Index: 145