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

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

Neuron 4072 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: 0.2644. Min Range: -0.2644

Max Act: 0.2644. Min Act: -0.0000

Data Index: 908742 (C4 (Web Text))

Max Activating Token Index: 229

Text #1

Max Range: 0.2644. Min Range: -0.2644

Max Act: 0.2305. Min Act: -0.0000

Data Index: 374789 (C4 (Web Text))

Max Activating Token Index: 215

Text #2

Max Range: 0.2644. Min Range: -0.2644

Max Act: 0.2367. Min Act: -0.0000

Data Index: 73647 (C4 (Web Text))

Max Activating Token Index: 937

Text #3

Max Range: 0.2644. Min Range: -0.2644

Max Act: 0.2265. Min Act: -0.0000

Data Index: 1226513 (C4 (Web Text))

Max Activating Token Index: 401

Text #4

Max Range: 0.2644. Min Range: -0.2644

Max Act: 0.2411. Min Act: -0.0000

Data Index: 1227469 (C4 (Web Text))

Max Activating Token Index: 732

Text #5

Max Range: 0.2644. Min Range: -0.2644

Max Act: 0.2244. Min Act: -0.0000

Data Index: 1104810 (C4 (Web Text))

Max Activating Token Index: 557

Text #6

Max Range: 0.2644. Min Range: -0.2644

Max Act: 0.2154. Min Act: -0.0000

Data Index: 653808 (C4 (Web Text))

Max Activating Token Index: 48

Text #7

Max Range: 0.2644. Min Range: -0.2644

Max Act: 0.2076. Min Act: -0.0000

Data Index: 6658 (C4 (Web Text))

Max Activating Token Index: 89

Text #8

Max Range: 0.2644. Min Range: -0.2644

Max Act: 0.1995. Min Act: -0.0000

Data Index: 986952 (C4 (Web Text))

Max Activating Token Index: 599

Text #9

Max Range: 0.2644. Min Range: -0.2644

Max Act: 0.2065. Min Act: -0.0000

Data Index: 1155865 (C4 (Web Text))

Max Activating Token Index: 784

Text #10

Max Range: 0.2644. Min Range: -0.2644

Max Act: 0.2060. Min Act: -0.0000

Data Index: 341063 (C4 (Web Text))

Max Activating Token Index: 1008

Text #11

Max Range: 0.2644. Min Range: -0.2644

Max Act: 0.2006. Min Act: -0.0000

Data Index: 621649 (C4 (Web Text))

Max Activating Token Index: 111

Text #12

Max Range: 0.2644. Min Range: -0.2644

Max Act: 0.1975. Min Act: -0.0000

Data Index: 60527 (C4 (Web Text))

Max Activating Token Index: 631

Text #13

Max Range: 0.2644. Min Range: -0.2644

Max Act: 0.1982. Min Act: -0.0000

Data Index: 1285565 (C4 (Web Text))

Max Activating Token Index: 645

Text #14

Max Range: 0.2644. Min Range: -0.2644

Max Act: 0.1796. Min Act: -0.0000

Data Index: 1127216 (C4 (Web Text))

Max Activating Token Index: 393

Text #15

Max Range: 0.2644. Min Range: -0.2644

Max Act: 0.1828. Min Act: -0.0000

Data Index: 606112 (C4 (Web Text))

Max Activating Token Index: 410

Text #16

Max Range: 0.2644. Min Range: -0.2644

Max Act: 0.1867. Min Act: -0.0000

Data Index: 326871 (C4 (Web Text))

Max Activating Token Index: 281

Text #17

Max Range: 0.2644. Min Range: -0.2644

Max Act: 0.1800. Min Act: -0.0000

Data Index: 1221699 (C4 (Web Text))

Max Activating Token Index: 466

Text #18

Max Range: 0.2644. Min Range: -0.2644

Max Act: 0.1854. Min Act: -0.0000

Data Index: 787567 (C4 (Web Text))

Max Activating Token Index: 729

Text #19

Max Range: 0.2644. Min Range: -0.2644

Max Act: 0.1756. Min Act: -0.0000

Data Index: 977140 (C4 (Web Text))

Max Activating Token Index: 88