Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 611 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1217. Min Range: -0.1217

Max Act: 0.1217. Min Act: -0.0004

Data Index: 1152875 (C4 (Web Text))

Max Activating Token Index: 683

Text #1

Max Range: 0.1217. Min Range: -0.1217

Max Act: 0.0819. Min Act: -0.0004

Data Index: 403605 (C4 (Web Text))

Max Activating Token Index: 584

Text #2

Max Range: 0.1217. Min Range: -0.1217

Max Act: 0.1046. Min Act: -0.0004

Data Index: 1085175 (C4 (Web Text))

Max Activating Token Index: 1016

Text #3

Max Range: 0.1217. Min Range: -0.1217

Max Act: 0.0903. Min Act: -0.0004

Data Index: 136919 (C4 (Web Text))

Max Activating Token Index: 23

Text #4

Max Range: 0.1217. Min Range: -0.1217

Max Act: 0.0877. Min Act: -0.0004

Data Index: 1267469 (C4 (Web Text))

Max Activating Token Index: 915

Text #5

Max Range: 0.1217. Min Range: -0.1217

Max Act: 0.0903. Min Act: -0.0004

Data Index: 23140 (C4 (Web Text))

Max Activating Token Index: 564

Text #6

Max Range: 0.1217. Min Range: -0.1217

Max Act: 0.0867. Min Act: -0.0004

Data Index: 41095 (C4 (Web Text))

Max Activating Token Index: 208

Text #7

Max Range: 0.1217. Min Range: -0.1217

Max Act: 0.0856. Min Act: -0.0004

Data Index: 22496 (C4 (Web Text))

Max Activating Token Index: 447

Text #8

Max Range: 0.1217. Min Range: -0.1217

Max Act: 0.0790. Min Act: -0.0004

Data Index: 1352009 (C4 (Web Text))

Max Activating Token Index: 300

Text #9

Max Range: 0.1217. Min Range: -0.1217

Max Act: 0.0942. Min Act: -0.0004

Data Index: 444384 (C4 (Web Text))

Max Activating Token Index: 15

Text #10

Max Range: 0.1217. Min Range: -0.1217

Max Act: 0.0716. Min Act: -0.0004

Data Index: 1131101 (C4 (Web Text))

Max Activating Token Index: 837

Text #11

Max Range: 0.1217. Min Range: -0.1217

Max Act: 0.0891. Min Act: -0.0004

Data Index: 253638 (C4 (Web Text))

Max Activating Token Index: 383

Text #12

Max Range: 0.1217. Min Range: -0.1217

Max Act: 0.0918. Min Act: -0.0004

Data Index: 188379 (C4 (Web Text))

Max Activating Token Index: 944

Text #13

Max Range: 0.1217. Min Range: -0.1217

Max Act: 0.0938. Min Act: -0.0004

Data Index: 960218 (C4 (Web Text))

Max Activating Token Index: 205

Text #14

Max Range: 0.1217. Min Range: -0.1217

Max Act: 0.0780. Min Act: -0.0004

Data Index: 1233482 (C4 (Web Text))

Max Activating Token Index: 555

Text #15

Max Range: 0.1217. Min Range: -0.1217

Max Act: 0.0897. Min Act: -0.0004

Data Index: 172924 (C4 (Web Text))

Max Activating Token Index: 49

Text #16

Max Range: 0.1217. Min Range: -0.1217

Max Act: 0.0748. Min Act: -0.0004

Data Index: 102898 (C4 (Web Text))

Max Activating Token Index: 219

Text #17

Max Range: 0.1217. Min Range: -0.1217

Max Act: 0.0745. Min Act: -0.0004

Data Index: 650937 (C4 (Web Text))

Max Activating Token Index: 342

Text #18

Max Range: 0.1217. Min Range: -0.1217

Max Act: 0.0894. Min Act: -0.0004

Data Index: 477814 (C4 (Web Text))

Max Activating Token Index: 167

Text #19

Max Range: 0.1217. Min Range: -0.1217

Max Act: 0.0852. Min Act: -0.0004

Data Index: 809273 (C4 (Web Text))

Max Activating Token Index: 476