Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 582 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.1024. Min Act: -0.0001

Data Index: 382302 (C4 (Web Text))

Max Activating Token Index: 410

Text #1

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0938. Min Act: -0.0001

Data Index: 1087795 (C4 (Web Text))

Max Activating Token Index: 504

Text #2

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0914. Min Act: -0.0001

Data Index: 463764 (C4 (Web Text))

Max Activating Token Index: 195

Text #3

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0887. Min Act: -0.0001

Data Index: 410370 (C4 (Web Text))

Max Activating Token Index: 777

Text #4

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0843. Min Act: -0.0001

Data Index: 92447 (C4 (Web Text))

Max Activating Token Index: 816

Text #5

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0780. Min Act: -0.0001

Data Index: 550561 (C4 (Web Text))

Max Activating Token Index: 757

Text #6

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0911. Min Act: -0.0001

Data Index: 69566 (C4 (Web Text))

Max Activating Token Index: 901

Text #7

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0830. Min Act: -0.0001

Data Index: 960530 (C4 (Web Text))

Max Activating Token Index: 755

Text #8

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0773. Min Act: -0.0001

Data Index: 1303056 (C4 (Web Text))

Max Activating Token Index: 863

Text #9

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0814. Min Act: -0.0001

Data Index: 465650 (C4 (Web Text))

Max Activating Token Index: 546

Text #10

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0821. Min Act: -0.0001

Data Index: 1085301 (C4 (Web Text))

Max Activating Token Index: 774

Text #11

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0795. Min Act: -0.0001

Data Index: 716176 (C4 (Web Text))

Max Activating Token Index: 503

Text #12

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0762. Min Act: -0.0001

Data Index: 425504 (C4 (Web Text))

Max Activating Token Index: 656

Text #13

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0850. Min Act: -0.0001

Data Index: 1133157 (C4 (Web Text))

Max Activating Token Index: 504

Text #14

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0780. Min Act: -0.0001

Data Index: 89618 (C4 (Web Text))

Max Activating Token Index: 695

Text #15

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0815. Min Act: -0.0001

Data Index: 1209505 (C4 (Web Text))

Max Activating Token Index: 532

Text #16

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0809. Min Act: -0.0001

Data Index: 985437 (C4 (Web Text))

Max Activating Token Index: 194

Text #17

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0810. Min Act: -0.0001

Data Index: 1133452 (C4 (Web Text))

Max Activating Token Index: 218

Text #18

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0774. Min Act: -0.0001

Data Index: 655743 (C4 (Web Text))

Max Activating Token Index: 377

Text #19

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0773. Min Act: -0.0001

Data Index: 88988 (C4 (Web Text))

Max Activating Token Index: 437