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

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

Neuron 3785 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1254. Min Range: -0.1254

Max Act: 0.1244. Min Act: -0.0000

Data Index: 54241 (C4 (Web Text))

Max Activating Token Index: 782

Text #1

Max Range: 0.1254. Min Range: -0.1254

Max Act: 0.1254. Min Act: -0.0000

Data Index: 454129 (C4 (Web Text))

Max Activating Token Index: 952

Text #2

Max Range: 0.1254. Min Range: -0.1254

Max Act: 0.1102. Min Act: -0.0000

Data Index: 829293 (C4 (Web Text))

Max Activating Token Index: 527

Text #3

Max Range: 0.1254. Min Range: -0.1254

Max Act: 0.1005. Min Act: -0.0000

Data Index: 1288380 (C4 (Web Text))

Max Activating Token Index: 511

Text #4

Max Range: 0.1254. Min Range: -0.1254

Max Act: 0.0977. Min Act: -0.0000

Data Index: 601134 (C4 (Web Text))

Max Activating Token Index: 249

Text #5

Max Range: 0.1254. Min Range: -0.1254

Max Act: 0.0989. Min Act: -0.0000

Data Index: 1090417 (C4 (Web Text))

Max Activating Token Index: 649

Text #6

Max Range: 0.1254. Min Range: -0.1254

Max Act: 0.0996. Min Act: -0.0000

Data Index: 1080435 (C4 (Web Text))

Max Activating Token Index: 228

Text #7

Max Range: 0.1254. Min Range: -0.1254

Max Act: 0.0913. Min Act: -0.0000

Data Index: 1019730 (C4 (Web Text))

Max Activating Token Index: 241

Text #8

Max Range: 0.1254. Min Range: -0.1254

Max Act: 0.0869. Min Act: -0.0000

Data Index: 1082742 (C4 (Web Text))

Max Activating Token Index: 968

Text #9

Max Range: 0.1254. Min Range: -0.1254

Max Act: 0.0909. Min Act: -0.0000

Data Index: 903467 (C4 (Web Text))

Max Activating Token Index: 1021

Text #10

Max Range: 0.1254. Min Range: -0.1254

Max Act: 0.0857. Min Act: -0.0000

Data Index: 110388 (C4 (Web Text))

Max Activating Token Index: 103

Text #11

Max Range: 0.1254. Min Range: -0.1254

Max Act: 0.0856. Min Act: -0.0000

Data Index: 1570583 (Python Code)

Max Activating Token Index: 322

Text #12

Max Range: 0.1254. Min Range: -0.1254

Max Act: 0.0784. Min Act: -0.0000

Data Index: 1160717 (C4 (Web Text))

Max Activating Token Index: 1018

Text #13

Max Range: 0.1254. Min Range: -0.1254

Max Act: 0.0844. Min Act: -0.0000

Data Index: 1127753 (C4 (Web Text))

Max Activating Token Index: 573

Text #14

Max Range: 0.1254. Min Range: -0.1254

Max Act: 0.0759. Min Act: -0.0000

Data Index: 1235503 (C4 (Web Text))

Max Activating Token Index: 838

Text #15

Max Range: 0.1254. Min Range: -0.1254

Max Act: 0.0746. Min Act: -0.0000

Data Index: 1581836 (Python Code)

Max Activating Token Index: 849

Text #16

Max Range: 0.1254. Min Range: -0.1254

Max Act: 0.0812. Min Act: -0.0000

Data Index: 171754 (C4 (Web Text))

Max Activating Token Index: 694

Text #17

Max Range: 0.1254. Min Range: -0.1254

Max Act: 0.0757. Min Act: -0.0000

Data Index: 1286078 (C4 (Web Text))

Max Activating Token Index: 186

Text #18

Max Range: 0.1254. Min Range: -0.1254

Max Act: 0.0779. Min Act: -0.0000

Data Index: 1117588 (C4 (Web Text))

Max Activating Token Index: 186

Text #19

Max Range: 0.1254. Min Range: -0.1254

Max Act: 0.0740. Min Act: -0.0000

Data Index: 600958 (C4 (Web Text))

Max Activating Token Index: 79