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

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

Neuron 943 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.1260. Min Act: -0.0000

Data Index: 566693 (C4 (Web Text))

Max Activating Token Index: 649

Text #1

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.1189. Min Act: -0.0000

Data Index: 207729 (C4 (Web Text))

Max Activating Token Index: 28

Text #2

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.1018. Min Act: -0.0000

Data Index: 168081 (C4 (Web Text))

Max Activating Token Index: 454

Text #3

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.1053. Min Act: -0.0000

Data Index: 1600300 (Python Code)

Max Activating Token Index: 699

Text #4

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.0991. Min Act: -0.0000

Data Index: 1365006 (Python Code)

Max Activating Token Index: 296

Text #5

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.0959. Min Act: -0.0000

Data Index: 54936 (C4 (Web Text))

Max Activating Token Index: 350

Text #6

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.0910. Min Act: -0.0000

Data Index: 175167 (C4 (Web Text))

Max Activating Token Index: 619

Text #7

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.0868. Min Act: -0.0000

Data Index: 772433 (C4 (Web Text))

Max Activating Token Index: 608

Text #8

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.0821. Min Act: -0.0000

Data Index: 1432348 (Python Code)

Max Activating Token Index: 258

Text #9

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.0857. Min Act: -0.0000

Data Index: 105051 (C4 (Web Text))

Max Activating Token Index: 477

Text #10

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.0878. Min Act: -0.0000

Data Index: 1651984 (Python Code)

Max Activating Token Index: 778

Text #11

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.0879. Min Act: -0.0000

Data Index: 716704 (C4 (Web Text))

Max Activating Token Index: 834

Text #12

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.0873. Min Act: -0.0000

Data Index: 758533 (C4 (Web Text))

Max Activating Token Index: 301

Text #13

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.0982. Min Act: -0.0000

Data Index: 1628172 (Python Code)

Max Activating Token Index: 890

Text #14

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.0866. Min Act: -0.0000

Data Index: 169749 (C4 (Web Text))

Max Activating Token Index: 210

Text #15

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.0862. Min Act: -0.0000

Data Index: 137855 (C4 (Web Text))

Max Activating Token Index: 33

Text #16

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.0883. Min Act: -0.0000

Data Index: 1146851 (C4 (Web Text))

Max Activating Token Index: 972

Text #17

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.0849. Min Act: -0.0000

Data Index: 386770 (C4 (Web Text))

Max Activating Token Index: 992

Text #18

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.0849. Min Act: -0.0000

Data Index: 1491938 (Python Code)

Max Activating Token Index: 931

Text #19

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.0905. Min Act: -0.0000

Data Index: 959432 (C4 (Web Text))

Max Activating Token Index: 946