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

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

Neuron 3228 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: 0.3482. Min Range: -0.3482

Max Act: 0.3482. Min Act: -0.0000

Data Index: 892819 (C4 (Web Text))

Max Activating Token Index: 338

Text #1

Max Range: 0.3482. Min Range: -0.3482

Max Act: 0.3211. Min Act: -0.0000

Data Index: 786219 (C4 (Web Text))

Max Activating Token Index: 978

Text #2

Max Range: 0.3482. Min Range: -0.3482

Max Act: 0.3153. Min Act: -0.0001

Data Index: 1147129 (C4 (Web Text))

Max Activating Token Index: 333

Text #3

Max Range: 0.3482. Min Range: -0.3482

Max Act: 0.3251. Min Act: -0.0000

Data Index: 1042815 (C4 (Web Text))

Max Activating Token Index: 234

Text #4

Max Range: 0.3482. Min Range: -0.3482

Max Act: 0.3117. Min Act: -0.0000

Data Index: 848222 (C4 (Web Text))

Max Activating Token Index: 671

Text #5

Max Range: 0.3482. Min Range: -0.3482

Max Act: 0.3092. Min Act: -0.0000

Data Index: 1181319 (C4 (Web Text))

Max Activating Token Index: 104

Text #6

Max Range: 0.3482. Min Range: -0.3482

Max Act: 0.3090. Min Act: -0.0000

Data Index: 396552 (C4 (Web Text))

Max Activating Token Index: 451

Text #7

Max Range: 0.3482. Min Range: -0.3482

Max Act: 0.3074. Min Act: -0.0000

Data Index: 1569253 (Python Code)

Max Activating Token Index: 605

Text #8

Max Range: 0.3482. Min Range: -0.3482

Max Act: 0.2928. Min Act: -0.0000

Data Index: 341246 (C4 (Web Text))

Max Activating Token Index: 339

Text #9

Max Range: 0.3482. Min Range: -0.3482

Max Act: 0.2891. Min Act: -0.0000

Data Index: 1107810 (C4 (Web Text))

Max Activating Token Index: 689

Text #10

Max Range: 0.3482. Min Range: -0.3482

Max Act: 0.3070. Min Act: -0.0000

Data Index: 401537 (C4 (Web Text))

Max Activating Token Index: 771

Text #11

Max Range: 0.3482. Min Range: -0.3482

Max Act: 0.2891. Min Act: -0.0000

Data Index: 1332514 (C4 (Web Text))

Max Activating Token Index: 301

Text #12

Max Range: 0.3482. Min Range: -0.3482

Max Act: 0.3060. Min Act: -0.0000

Data Index: 39210 (C4 (Web Text))

Max Activating Token Index: 911

Text #13

Max Range: 0.3482. Min Range: -0.3482

Max Act: 0.2972. Min Act: -0.0000

Data Index: 412138 (C4 (Web Text))

Max Activating Token Index: 992

Text #14

Max Range: 0.3482. Min Range: -0.3482

Max Act: 0.2862. Min Act: -0.0000

Data Index: 1066003 (C4 (Web Text))

Max Activating Token Index: 889

Text #15

Max Range: 0.3482. Min Range: -0.3482

Max Act: 0.2842. Min Act: -0.0000

Data Index: 86831 (C4 (Web Text))

Max Activating Token Index: 137

Text #16

Max Range: 0.3482. Min Range: -0.3482

Max Act: 0.2942. Min Act: -0.0000

Data Index: 553376 (C4 (Web Text))

Max Activating Token Index: 920

Text #17

Max Range: 0.3482. Min Range: -0.3482

Max Act: 0.3037. Min Act: -0.0000

Data Index: 582987 (C4 (Web Text))

Max Activating Token Index: 339

Text #18

Max Range: 0.3482. Min Range: -0.3482

Max Act: 0.2918. Min Act: -0.0000

Data Index: 1341627 (C4 (Web Text))

Max Activating Token Index: 908

Text #19

Max Range: 0.3482. Min Range: -0.3482

Max Act: 0.2928. Min Act: -0.0000

Data Index: 1256470 (C4 (Web Text))

Max Activating Token Index: 81