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

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

Neuron 2199 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: 0.3742. Min Range: -0.3742

Max Act: 0.3644. Min Act: -0.0000

Data Index: 806322 (C4 (Web Text))

Max Activating Token Index: 18

Text #1

Max Range: 0.3742. Min Range: -0.3742

Max Act: 0.3742. Min Act: -0.0000

Data Index: 479400 (C4 (Web Text))

Max Activating Token Index: 29

Text #2

Max Range: 0.3742. Min Range: -0.3742

Max Act: 0.3518. Min Act: -0.0000

Data Index: 1193298 (C4 (Web Text))

Max Activating Token Index: 578

Text #3

Max Range: 0.3742. Min Range: -0.3742

Max Act: 0.3356. Min Act: -0.0000

Data Index: 131894 (C4 (Web Text))

Max Activating Token Index: 674

Text #4

Max Range: 0.3742. Min Range: -0.3742

Max Act: 0.3118. Min Act: -0.0000

Data Index: 397170 (C4 (Web Text))

Max Activating Token Index: 16

Text #5

Max Range: 0.3742. Min Range: -0.3742

Max Act: 0.3111. Min Act: -0.0000

Data Index: 1210736 (C4 (Web Text))

Max Activating Token Index: 625

Text #6

Max Range: 0.3742. Min Range: -0.3742

Max Act: 0.3018. Min Act: -0.0000

Data Index: 4784 (C4 (Web Text))

Max Activating Token Index: 16

Text #7

Max Range: 0.3742. Min Range: -0.3742

Max Act: 0.3110. Min Act: -0.0000

Data Index: 896324 (C4 (Web Text))

Max Activating Token Index: 15

Text #8

Max Range: 0.3742. Min Range: -0.3742

Max Act: 0.3098. Min Act: -0.0000

Data Index: 816304 (C4 (Web Text))

Max Activating Token Index: 301

Text #9

Max Range: 0.3742. Min Range: -0.3742

Max Act: 0.2979. Min Act: -0.0000

Data Index: 1344873 (C4 (Web Text))

Max Activating Token Index: 848

Text #10

Max Range: 0.3742. Min Range: -0.3742

Max Act: 0.2903. Min Act: -0.0000

Data Index: 812466 (C4 (Web Text))

Max Activating Token Index: 6

Text #11

Max Range: 0.3742. Min Range: -0.3742

Max Act: 0.2850. Min Act: -0.0000

Data Index: 233346 (C4 (Web Text))

Max Activating Token Index: 23

Text #12

Max Range: 0.3742. Min Range: -0.3742

Max Act: 0.3033. Min Act: -0.0000

Data Index: 168237 (C4 (Web Text))

Max Activating Token Index: 610

Text #13

Max Range: 0.3742. Min Range: -0.3742

Max Act: 0.2816. Min Act: -0.0000

Data Index: 799794 (C4 (Web Text))

Max Activating Token Index: 803

Text #14

Max Range: 0.3742. Min Range: -0.3742

Max Act: 0.2996. Min Act: -0.0000

Data Index: 316570 (C4 (Web Text))

Max Activating Token Index: 301

Text #15

Max Range: 0.3742. Min Range: -0.3742

Max Act: 0.2887. Min Act: -0.0000

Data Index: 986097 (C4 (Web Text))

Max Activating Token Index: 945

Text #16

Max Range: 0.3742. Min Range: -0.3742

Max Act: 0.2723. Min Act: -0.0000

Data Index: 1009718 (C4 (Web Text))

Max Activating Token Index: 728

Text #17

Max Range: 0.3742. Min Range: -0.3742

Max Act: 0.2841. Min Act: -0.0000

Data Index: 763661 (C4 (Web Text))

Max Activating Token Index: 860

Text #18

Max Range: 0.3742. Min Range: -0.3742

Max Act: 0.2828. Min Act: -0.0000

Data Index: 414648 (C4 (Web Text))

Max Activating Token Index: 82

Text #19

Max Range: 0.3742. Min Range: -0.3742

Max Act: 0.2735. Min Act: -0.0000

Data Index: 140622 (C4 (Web Text))

Max Activating Token Index: 160