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

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

Neuron 4839 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4267. Min Range: -0.4267

Max Act: 0.4076. Min Act: -0.0000

Data Index: 163269 (C4 (Web Text))

Max Activating Token Index: 263

Text #1

Max Range: 0.4267. Min Range: -0.4267

Max Act: 0.3331. Min Act: -0.0000

Data Index: 1085357 (C4 (Web Text))

Max Activating Token Index: 649

Text #2

Max Range: 0.4267. Min Range: -0.4267

Max Act: 0.4267. Min Act: -0.0000

Data Index: 1014625 (C4 (Web Text))

Max Activating Token Index: 681

Text #3

Max Range: 0.4267. Min Range: -0.4267

Max Act: 0.3411. Min Act: -0.0000

Data Index: 389455 (C4 (Web Text))

Max Activating Token Index: 52

Text #4

Max Range: 0.4267. Min Range: -0.4267

Max Act: 0.3388. Min Act: -0.0000

Data Index: 213356 (C4 (Web Text))

Max Activating Token Index: 11

Text #5

Max Range: 0.4267. Min Range: -0.4267

Max Act: 0.3437. Min Act: -0.0000

Data Index: 52446 (C4 (Web Text))

Max Activating Token Index: 884

Text #6

Max Range: 0.4267. Min Range: -0.4267

Max Act: 0.3023. Min Act: -0.0000

Data Index: 1023605 (C4 (Web Text))

Max Activating Token Index: 824

Text #7

Max Range: 0.4267. Min Range: -0.4267

Max Act: 0.2772. Min Act: -0.0000

Data Index: 1155065 (C4 (Web Text))

Max Activating Token Index: 985

Text #8

Max Range: 0.4267. Min Range: -0.4267

Max Act: 0.2901. Min Act: -0.0000

Data Index: 157553 (C4 (Web Text))

Max Activating Token Index: 889

Text #9

Max Range: 0.4267. Min Range: -0.4267

Max Act: 0.3253. Min Act: -0.0000

Data Index: 20873 (C4 (Web Text))

Max Activating Token Index: 333

Text #10

Max Range: 0.4267. Min Range: -0.4267

Max Act: 0.3047. Min Act: -0.0000

Data Index: 1011201 (C4 (Web Text))

Max Activating Token Index: 674

Text #11

Max Range: 0.4267. Min Range: -0.4267

Max Act: 0.3023. Min Act: -0.0000

Data Index: 731914 (C4 (Web Text))

Max Activating Token Index: 133

Text #12

Max Range: 0.4267. Min Range: -0.4267

Max Act: 0.2808. Min Act: -0.0000

Data Index: 1117816 (C4 (Web Text))

Max Activating Token Index: 682

Text #13

Max Range: 0.4267. Min Range: -0.4267

Max Act: 0.2692. Min Act: -0.0000

Data Index: 742972 (C4 (Web Text))

Max Activating Token Index: 11

Text #14

Max Range: 0.4267. Min Range: -0.4267

Max Act: 0.2859. Min Act: -0.0000

Data Index: 1307857 (C4 (Web Text))

Max Activating Token Index: 793

Text #15

Max Range: 0.4267. Min Range: -0.4267

Max Act: 0.2974. Min Act: -0.0000

Data Index: 1056105 (C4 (Web Text))

Max Activating Token Index: 70

Text #16

Max Range: 0.4267. Min Range: -0.4267

Max Act: 0.2585. Min Act: -0.0000

Data Index: 88467 (C4 (Web Text))

Max Activating Token Index: 608

Text #17

Max Range: 0.4267. Min Range: -0.4267

Max Act: 0.2539. Min Act: -0.0000

Data Index: 38635 (C4 (Web Text))

Max Activating Token Index: 711

Text #18

Max Range: 0.4267. Min Range: -0.4267

Max Act: 0.2791. Min Act: -0.0000

Data Index: 876319 (C4 (Web Text))

Max Activating Token Index: 316

Text #19

Max Range: 0.4267. Min Range: -0.4267

Max Act: 0.2602. Min Act: -0.0000

Data Index: 111354 (C4 (Web Text))

Max Activating Token Index: 388