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

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

Neuron 930 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7571. Min Range: -0.7571

Max Act: 0.7571. Min Act: -0.0000

Data Index: 343062 (C4 (Web Text))

Max Activating Token Index: 684

Text #1

Max Range: 0.7571. Min Range: -0.7571

Max Act: 0.6834. Min Act: -0.0000

Data Index: 376659 (C4 (Web Text))

Max Activating Token Index: 934

Text #2

Max Range: 0.7571. Min Range: -0.7571

Max Act: 0.6293. Min Act: -0.0000

Data Index: 764790 (C4 (Web Text))

Max Activating Token Index: 680

Text #3

Max Range: 0.7571. Min Range: -0.7571

Max Act: 0.6320. Min Act: -0.0000

Data Index: 194450 (C4 (Web Text))

Max Activating Token Index: 166

Text #4

Max Range: 0.7571. Min Range: -0.7571

Max Act: 0.6525. Min Act: -0.0000

Data Index: 1074577 (C4 (Web Text))

Max Activating Token Index: 108

Text #5

Max Range: 0.7571. Min Range: -0.7571

Max Act: 0.6483. Min Act: -0.0000

Data Index: 22091 (C4 (Web Text))

Max Activating Token Index: 1009

Text #6

Max Range: 0.7571. Min Range: -0.7571

Max Act: 0.5881. Min Act: -0.0000

Data Index: 77883 (C4 (Web Text))

Max Activating Token Index: 777

Text #7

Max Range: 0.7571. Min Range: -0.7571

Max Act: 0.6023. Min Act: -0.0000

Data Index: 716411 (C4 (Web Text))

Max Activating Token Index: 592

Text #8

Max Range: 0.7571. Min Range: -0.7571

Max Act: 0.5942. Min Act: -0.0000

Data Index: 1010800 (C4 (Web Text))

Max Activating Token Index: 865

Text #9

Max Range: 0.7571. Min Range: -0.7571

Max Act: 0.6034. Min Act: -0.0000

Data Index: 421780 (C4 (Web Text))

Max Activating Token Index: 470

Text #10

Max Range: 0.7571. Min Range: -0.7571

Max Act: 0.5586. Min Act: -0.0000

Data Index: 411017 (C4 (Web Text))

Max Activating Token Index: 190

Text #11

Max Range: 0.7571. Min Range: -0.7571

Max Act: 0.5985. Min Act: -0.0000

Data Index: 388264 (C4 (Web Text))

Max Activating Token Index: 629

Text #12

Max Range: 0.7571. Min Range: -0.7571

Max Act: 0.5948. Min Act: -0.0000

Data Index: 823822 (C4 (Web Text))

Max Activating Token Index: 908

Text #13

Max Range: 0.7571. Min Range: -0.7571

Max Act: 0.6128. Min Act: -0.0000

Data Index: 1042561 (C4 (Web Text))

Max Activating Token Index: 810

Text #14

Max Range: 0.7571. Min Range: -0.7571

Max Act: 0.5959. Min Act: -0.0000

Data Index: 905016 (C4 (Web Text))

Max Activating Token Index: 981

Text #15

Max Range: 0.7571. Min Range: -0.7571

Max Act: 0.5704. Min Act: -0.0000

Data Index: 497888 (C4 (Web Text))

Max Activating Token Index: 31

Text #16

Max Range: 0.7571. Min Range: -0.7571

Max Act: 0.5880. Min Act: -0.0000

Data Index: 43107 (C4 (Web Text))

Max Activating Token Index: 720

Text #17

Max Range: 0.7571. Min Range: -0.7571

Max Act: 0.5621. Min Act: -0.0000

Data Index: 85379 (C4 (Web Text))

Max Activating Token Index: 7

Text #18

Max Range: 0.7571. Min Range: -0.7571

Max Act: 0.5841. Min Act: -0.0000

Data Index: 79975 (C4 (Web Text))

Max Activating Token Index: 902

Text #19

Max Range: 0.7571. Min Range: -0.7571

Max Act: 0.5871. Min Act: -0.0000

Data Index: 701262 (C4 (Web Text))

Max Activating Token Index: 439