Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4531 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1307. Min Range: -0.1307

Max Act: 0.1307. Min Act: -0.0002

Data Index: 967537 (C4 (Web Text))

Max Activating Token Index: 366

Text #1

Max Range: 0.1307. Min Range: -0.1307

Max Act: 0.1138. Min Act: -0.0002

Data Index: 623132 (C4 (Web Text))

Max Activating Token Index: 119

Text #2

Max Range: 0.1307. Min Range: -0.1307

Max Act: 0.1028. Min Act: -0.0002

Data Index: 130172 (C4 (Web Text))

Max Activating Token Index: 38

Text #3

Max Range: 0.1307. Min Range: -0.1307

Max Act: 0.1029. Min Act: -0.0002

Data Index: 927525 (C4 (Web Text))

Max Activating Token Index: 755

Text #4

Max Range: 0.1307. Min Range: -0.1307

Max Act: 0.0977. Min Act: -0.0002

Data Index: 231378 (C4 (Web Text))

Max Activating Token Index: 429

Text #5

Max Range: 0.1307. Min Range: -0.1307

Max Act: 0.0972. Min Act: -0.0002

Data Index: 889366 (C4 (Web Text))

Max Activating Token Index: 578

Text #6

Max Range: 0.1307. Min Range: -0.1307

Max Act: 0.0960. Min Act: -0.0002

Data Index: 629174 (C4 (Web Text))

Max Activating Token Index: 180

Text #7

Max Range: 0.1307. Min Range: -0.1307

Max Act: 0.0920. Min Act: -0.0002

Data Index: 52798 (C4 (Web Text))

Max Activating Token Index: 47

Text #8

Max Range: 0.1307. Min Range: -0.1307

Max Act: 0.0867. Min Act: -0.0002

Data Index: 613804 (C4 (Web Text))

Max Activating Token Index: 253

Text #9

Max Range: 0.1307. Min Range: -0.1307

Max Act: 0.0930. Min Act: -0.0002

Data Index: 316614 (C4 (Web Text))

Max Activating Token Index: 716

Text #10

Max Range: 0.1307. Min Range: -0.1307

Max Act: 0.0947. Min Act: -0.0002

Data Index: 472447 (C4 (Web Text))

Max Activating Token Index: 294

Text #11

Max Range: 0.1307. Min Range: -0.1307

Max Act: 0.0908. Min Act: -0.0002

Data Index: 79337 (C4 (Web Text))

Max Activating Token Index: 879

Text #12

Max Range: 0.1307. Min Range: -0.1307

Max Act: 0.0903. Min Act: -0.0002

Data Index: 853473 (C4 (Web Text))

Max Activating Token Index: 538

Text #13

Max Range: 0.1307. Min Range: -0.1307

Max Act: 0.0888. Min Act: -0.0002

Data Index: 1354513 (C4 (Web Text))

Max Activating Token Index: 366

Text #14

Max Range: 0.1307. Min Range: -0.1307

Max Act: 0.0877. Min Act: -0.0002

Data Index: 1263577 (C4 (Web Text))

Max Activating Token Index: 556

Text #15

Max Range: 0.1307. Min Range: -0.1307

Max Act: 0.0852. Min Act: -0.0002

Data Index: 873280 (C4 (Web Text))

Max Activating Token Index: 168

Text #16

Max Range: 0.1307. Min Range: -0.1307

Max Act: 0.0849. Min Act: -0.0002

Data Index: 350499 (C4 (Web Text))

Max Activating Token Index: 627

Text #17

Max Range: 0.1307. Min Range: -0.1307

Max Act: 0.0874. Min Act: -0.0002

Data Index: 788911 (C4 (Web Text))

Max Activating Token Index: 173

Text #18

Max Range: 0.1307. Min Range: -0.1307

Max Act: 0.0894. Min Act: -0.0002

Data Index: 1166747 (C4 (Web Text))

Max Activating Token Index: 486

Text #19

Max Range: 0.1307. Min Range: -0.1307

Max Act: 0.0805. Min Act: -0.0002

Data Index: 195694 (C4 (Web Text))

Max Activating Token Index: 305