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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 464 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1996. Min Range: -2.1996

Max Act: 2.1996. Min Act: -0.0000

Data Index: 88532 (C4 (Web Text))

Max Activating Token Index: 189

Text #1

Max Range: 2.1996. Min Range: -2.1996

Max Act: 1.7053. Min Act: -0.0000

Data Index: 1304006 (C4 (Web Text))

Max Activating Token Index: 283

Text #2

Max Range: 2.1996. Min Range: -2.1996

Max Act: 1.6882. Min Act: -0.0000

Data Index: 1043928 (C4 (Web Text))

Max Activating Token Index: 528

Text #3

Max Range: 2.1996. Min Range: -2.1996

Max Act: 1.5706. Min Act: -0.0000

Data Index: 930061 (C4 (Web Text))

Max Activating Token Index: 78

Text #4

Max Range: 2.1996. Min Range: -2.1996

Max Act: 1.5045. Min Act: -0.0000

Data Index: 200716 (C4 (Web Text))

Max Activating Token Index: 501

Text #5

Max Range: 2.1996. Min Range: -2.1996

Max Act: 1.4964. Min Act: -0.0000

Data Index: 1126064 (C4 (Web Text))

Max Activating Token Index: 730

Text #6

Max Range: 2.1996. Min Range: -2.1996

Max Act: 1.4727. Min Act: -0.0000

Data Index: 1148234 (C4 (Web Text))

Max Activating Token Index: 326

Text #7

Max Range: 2.1996. Min Range: -2.1996

Max Act: 1.4824. Min Act: -0.0000

Data Index: 324880 (C4 (Web Text))

Max Activating Token Index: 644

Text #8

Max Range: 2.1996. Min Range: -2.1996

Max Act: 1.3377. Min Act: -0.0000

Data Index: 805113 (C4 (Web Text))

Max Activating Token Index: 657

Text #9

Max Range: 2.1996. Min Range: -2.1996

Max Act: 1.3281. Min Act: -0.0000

Data Index: 1048359 (C4 (Web Text))

Max Activating Token Index: 230

Text #10

Max Range: 2.1996. Min Range: -2.1996

Max Act: 1.2897. Min Act: -0.0000

Data Index: 364185 (C4 (Web Text))

Max Activating Token Index: 543

Text #11

Max Range: 2.1996. Min Range: -2.1996

Max Act: 1.2640. Min Act: -0.0000

Data Index: 434794 (C4 (Web Text))

Max Activating Token Index: 666

Text #12

Max Range: 2.1996. Min Range: -2.1996

Max Act: 1.2468. Min Act: -0.0000

Data Index: 987195 (C4 (Web Text))

Max Activating Token Index: 656

Text #13

Max Range: 2.1996. Min Range: -2.1996

Max Act: 1.2452. Min Act: -0.0000

Data Index: 1352209 (C4 (Web Text))

Max Activating Token Index: 869

Text #14

Max Range: 2.1996. Min Range: -2.1996

Max Act: 1.3047. Min Act: -0.0000

Data Index: 396100 (C4 (Web Text))

Max Activating Token Index: 837

Text #15

Max Range: 2.1996. Min Range: -2.1996

Max Act: 1.3848. Min Act: -0.0000

Data Index: 852601 (C4 (Web Text))

Max Activating Token Index: 268

Text #16

Max Range: 2.1996. Min Range: -2.1996

Max Act: 1.2323. Min Act: -0.0000

Data Index: 118147 (C4 (Web Text))

Max Activating Token Index: 548

Text #17

Max Range: 2.1996. Min Range: -2.1996

Max Act: 1.2707. Min Act: -0.0000

Data Index: 1280439 (C4 (Web Text))

Max Activating Token Index: 545

Text #18

Max Range: 2.1996. Min Range: -2.1996

Max Act: 1.1788. Min Act: -0.0000

Data Index: 455473 (C4 (Web Text))

Max Activating Token Index: 984

Text #19

Max Range: 2.1996. Min Range: -2.1996

Max Act: 1.2530. Min Act: -0.0000

Data Index: 1295630 (C4 (Web Text))

Max Activating Token Index: 821