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

Dataset: The Pile

Neuron 3565 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: 8.8390. Min Range: -8.8390

Max Act: 8.4791. Min Act: -0.0000

Data Index: 1072167 (The Pile)

Max Activating Token Index: 322

Text #1

Max Range: 8.8390. Min Range: -8.8390

Max Act: 8.7321. Min Act: -0.0000

Data Index: 214500 (The Pile)

Max Activating Token Index: 1019

Text #2

Max Range: 8.8390. Min Range: -8.8390

Max Act: 8.6944. Min Act: -0.0000

Data Index: 504441 (The Pile)

Max Activating Token Index: 681

Text #3

Max Range: 8.8390. Min Range: -8.8390

Max Act: 8.8390. Min Act: -0.0000

Data Index: 859442 (The Pile)

Max Activating Token Index: 98

Text #4

Max Range: 8.8390. Min Range: -8.8390

Max Act: 8.5917. Min Act: -0.0000

Data Index: 1922213 (The Pile)

Max Activating Token Index: 1017

Text #5

Max Range: 8.8390. Min Range: -8.8390

Max Act: 8.4505. Min Act: -0.0000

Data Index: 477982 (The Pile)

Max Activating Token Index: 812

Text #6

Max Range: 8.8390. Min Range: -8.8390

Max Act: 8.4446. Min Act: -0.0000

Data Index: 685846 (The Pile)

Max Activating Token Index: 613

Text #7

Max Range: 8.8390. Min Range: -8.8390

Max Act: 8.5293. Min Act: -0.0000

Data Index: 1437998 (The Pile)

Max Activating Token Index: 115

Text #8

Max Range: 8.8390. Min Range: -8.8390

Max Act: 8.3917. Min Act: -0.0000

Data Index: 1770951 (The Pile)

Max Activating Token Index: 454

Text #9

Max Range: 8.8390. Min Range: -8.8390

Max Act: 8.0324. Min Act: -0.0000

Data Index: 99926 (The Pile)

Max Activating Token Index: 195

Text #10

Max Range: 8.8390. Min Range: -8.8390

Max Act: 8.4016. Min Act: -0.0000

Data Index: 1066461 (The Pile)

Max Activating Token Index: 484

Text #11

Max Range: 8.8390. Min Range: -8.8390

Max Act: 8.0281. Min Act: -0.0000

Data Index: 152624 (The Pile)

Max Activating Token Index: 624

Text #12

Max Range: 8.8390. Min Range: -8.8390

Max Act: 8.1060. Min Act: -0.0000

Data Index: 332092 (The Pile)

Max Activating Token Index: 739

Text #13

Max Range: 8.8390. Min Range: -8.8390

Max Act: 7.9434. Min Act: -0.0000

Data Index: 1573835 (The Pile)

Max Activating Token Index: 225

Text #14

Max Range: 8.8390. Min Range: -8.8390

Max Act: 8.0891. Min Act: -0.0000

Data Index: 360137 (The Pile)

Max Activating Token Index: 275

Text #15

Max Range: 8.8390. Min Range: -8.8390

Max Act: 7.8096. Min Act: -0.0000

Data Index: 994673 (The Pile)

Max Activating Token Index: 393

Text #16

Max Range: 8.8390. Min Range: -8.8390

Max Act: 7.4376. Min Act: -0.0000

Data Index: 1717364 (The Pile)

Max Activating Token Index: 881

Text #17

Max Range: 8.8390. Min Range: -8.8390

Max Act: 8.0925. Min Act: -0.0000

Data Index: 1216565 (The Pile)

Max Activating Token Index: 587

Text #18

Max Range: 8.8390. Min Range: -8.8390

Max Act: 7.8606. Min Act: -0.0000

Data Index: 1479426 (The Pile)

Max Activating Token Index: 468

Text #19

Max Range: 8.8390. Min Range: -8.8390

Max Act: 8.0694. Min Act: -0.0000

Data Index: 1843120 (The Pile)

Max Activating Token Index: 700