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

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

Neuron 5108 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2309. Min Range: -1.2309

Max Act: 1.2191. Min Act: -0.0000

Data Index: 509522 (C4 (Web Text))

Max Activating Token Index: 359

Text #1

Max Range: 1.2309. Min Range: -1.2309

Max Act: 1.2309. Min Act: -0.0000

Data Index: 1147636 (C4 (Web Text))

Max Activating Token Index: 322

Text #2

Max Range: 1.2309. Min Range: -1.2309

Max Act: 1.1710. Min Act: -0.0000

Data Index: 1178812 (C4 (Web Text))

Max Activating Token Index: 1010

Text #3

Max Range: 1.2309. Min Range: -1.2309

Max Act: 1.0057. Min Act: -0.0000

Data Index: 930646 (C4 (Web Text))

Max Activating Token Index: 556

Text #4

Max Range: 1.2309. Min Range: -1.2309

Max Act: 1.0083. Min Act: -0.0000

Data Index: 1077276 (C4 (Web Text))

Max Activating Token Index: 365

Text #5

Max Range: 1.2309. Min Range: -1.2309

Max Act: 1.0326. Min Act: -0.0000

Data Index: 698604 (C4 (Web Text))

Max Activating Token Index: 684

Text #6

Max Range: 1.2309. Min Range: -1.2309

Max Act: 0.9536. Min Act: -0.0000

Data Index: 268910 (C4 (Web Text))

Max Activating Token Index: 565

Text #7

Max Range: 1.2309. Min Range: -1.2309

Max Act: 0.9370. Min Act: -0.0000

Data Index: 1312824 (C4 (Web Text))

Max Activating Token Index: 350

Text #8

Max Range: 1.2309. Min Range: -1.2309

Max Act: 0.9160. Min Act: 0.0000

Data Index: 918787 (C4 (Web Text))

Max Activating Token Index: 24

Text #9

Max Range: 1.2309. Min Range: -1.2309

Max Act: 0.8742. Min Act: -0.0000

Data Index: 323969 (C4 (Web Text))

Max Activating Token Index: 294

Text #10

Max Range: 1.2309. Min Range: -1.2309

Max Act: 0.8811. Min Act: -0.0000

Data Index: 226497 (C4 (Web Text))

Max Activating Token Index: 379

Text #11

Max Range: 1.2309. Min Range: -1.2309

Max Act: 0.8569. Min Act: 0.0000

Data Index: 123713 (C4 (Web Text))

Max Activating Token Index: 22

Text #12

Max Range: 1.2309. Min Range: -1.2309

Max Act: 0.8474. Min Act: -0.0000

Data Index: 1022256 (C4 (Web Text))

Max Activating Token Index: 727

Text #13

Max Range: 1.2309. Min Range: -1.2309

Max Act: 0.8675. Min Act: -0.0000

Data Index: 992437 (C4 (Web Text))

Max Activating Token Index: 268

Text #14

Max Range: 1.2309. Min Range: -1.2309

Max Act: 0.8157. Min Act: -0.0000

Data Index: 376955 (C4 (Web Text))

Max Activating Token Index: 759

Text #15

Max Range: 1.2309. Min Range: -1.2309

Max Act: 0.7979. Min Act: -0.0000

Data Index: 887931 (C4 (Web Text))

Max Activating Token Index: 158

Text #16

Max Range: 1.2309. Min Range: -1.2309

Max Act: 0.8438. Min Act: -0.0000

Data Index: 906450 (C4 (Web Text))

Max Activating Token Index: 149

Text #17

Max Range: 1.2309. Min Range: -1.2309

Max Act: 0.7753. Min Act: -0.0000

Data Index: 467862 (C4 (Web Text))

Max Activating Token Index: 359

Text #18

Max Range: 1.2309. Min Range: -1.2309

Max Act: 0.8308. Min Act: -0.0000

Data Index: 1160120 (C4 (Web Text))

Max Activating Token Index: 723

Text #19

Max Range: 1.2309. Min Range: -1.2309

Max Act: 0.8120. Min Act: -0.0000

Data Index: 94626 (C4 (Web Text))

Max Activating Token Index: 975