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

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

Neuron 2735 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.4149. Min Range: -1.4149

Max Act: 1.4149. Min Act: -0.0000

Data Index: 725706 (C4 (Web Text))

Max Activating Token Index: 480

Text #1

Max Range: 1.4149. Min Range: -1.4149

Max Act: 1.2892. Min Act: -0.0000

Data Index: 732702 (C4 (Web Text))

Max Activating Token Index: 1003

Text #2

Max Range: 1.4149. Min Range: -1.4149

Max Act: 1.1094. Min Act: -0.0000

Data Index: 758757 (C4 (Web Text))

Max Activating Token Index: 486

Text #3

Max Range: 1.4149. Min Range: -1.4149

Max Act: 1.1597. Min Act: -0.0000

Data Index: 1208185 (C4 (Web Text))

Max Activating Token Index: 577

Text #4

Max Range: 1.4149. Min Range: -1.4149

Max Act: 1.0986. Min Act: -0.0000

Data Index: 905121 (C4 (Web Text))

Max Activating Token Index: 215

Text #5

Max Range: 1.4149. Min Range: -1.4149

Max Act: 1.0557. Min Act: -0.0000

Data Index: 292837 (C4 (Web Text))

Max Activating Token Index: 28

Text #6

Max Range: 1.4149. Min Range: -1.4149

Max Act: 1.1259. Min Act: -0.0000

Data Index: 153297 (C4 (Web Text))

Max Activating Token Index: 62

Text #7

Max Range: 1.4149. Min Range: -1.4149

Max Act: 1.1215. Min Act: -0.0000

Data Index: 351297 (C4 (Web Text))

Max Activating Token Index: 853

Text #8

Max Range: 1.4149. Min Range: -1.4149

Max Act: 1.0219. Min Act: -0.0000

Data Index: 126771 (C4 (Web Text))

Max Activating Token Index: 944

Text #9

Max Range: 1.4149. Min Range: -1.4149

Max Act: 0.9942. Min Act: -0.0000

Data Index: 573816 (C4 (Web Text))

Max Activating Token Index: 381

Text #10

Max Range: 1.4149. Min Range: -1.4149

Max Act: 0.9908. Min Act: -0.0000

Data Index: 764239 (C4 (Web Text))

Max Activating Token Index: 930

Text #11

Max Range: 1.4149. Min Range: -1.4149

Max Act: 1.0663. Min Act: -0.0000

Data Index: 196401 (C4 (Web Text))

Max Activating Token Index: 854

Text #12

Max Range: 1.4149. Min Range: -1.4149

Max Act: 0.9238. Min Act: -0.0000

Data Index: 1016447 (C4 (Web Text))

Max Activating Token Index: 147

Text #13

Max Range: 1.4149. Min Range: -1.4149

Max Act: 0.9535. Min Act: -0.0000

Data Index: 1093691 (C4 (Web Text))

Max Activating Token Index: 959

Text #14

Max Range: 1.4149. Min Range: -1.4149

Max Act: 0.8996. Min Act: -0.0000

Data Index: 197884 (C4 (Web Text))

Max Activating Token Index: 517

Text #15

Max Range: 1.4149. Min Range: -1.4149

Max Act: 0.8803. Min Act: -0.0000

Data Index: 342413 (C4 (Web Text))

Max Activating Token Index: 635

Text #16

Max Range: 1.4149. Min Range: -1.4149

Max Act: 0.8535. Min Act: -0.0000

Data Index: 1333274 (C4 (Web Text))

Max Activating Token Index: 718

Text #17

Max Range: 1.4149. Min Range: -1.4149

Max Act: 0.8802. Min Act: -0.0000

Data Index: 192141 (C4 (Web Text))

Max Activating Token Index: 27

Text #18

Max Range: 1.4149. Min Range: -1.4149

Max Act: 0.8982. Min Act: -0.0000

Data Index: 263869 (C4 (Web Text))

Max Activating Token Index: 368

Text #19

Max Range: 1.4149. Min Range: -1.4149

Max Act: 0.8958. Min Act: -0.0000

Data Index: 565671 (C4 (Web Text))

Max Activating Token Index: 562