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

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

Neuron 1363 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1996. Min Range: -0.1996

Max Act: 0.1996. Min Act: -0.0001

Data Index: 433136 (C4 (Web Text))

Max Activating Token Index: 10

Text #1

Max Range: 0.1996. Min Range: -0.1996

Max Act: 0.1739. Min Act: -0.0001

Data Index: 253982 (C4 (Web Text))

Max Activating Token Index: 414

Text #2

Max Range: 0.1996. Min Range: -0.1996

Max Act: 0.1406. Min Act: -0.0001

Data Index: 144910 (C4 (Web Text))

Max Activating Token Index: 478

Text #3

Max Range: 0.1996. Min Range: -0.1996

Max Act: 0.1496. Min Act: -0.0001

Data Index: 464731 (C4 (Web Text))

Max Activating Token Index: 315

Text #4

Max Range: 0.1996. Min Range: -0.1996

Max Act: 0.1406. Min Act: -0.0001

Data Index: 461005 (C4 (Web Text))

Max Activating Token Index: 358

Text #5

Max Range: 0.1996. Min Range: -0.1996

Max Act: 0.1412. Min Act: -0.0001

Data Index: 236964 (C4 (Web Text))

Max Activating Token Index: 90

Text #6

Max Range: 0.1996. Min Range: -0.1996

Max Act: 0.1202. Min Act: -0.0001

Data Index: 1142430 (C4 (Web Text))

Max Activating Token Index: 558

Text #7

Max Range: 0.1996. Min Range: -0.1996

Max Act: 0.1215. Min Act: -0.0001

Data Index: 421683 (C4 (Web Text))

Max Activating Token Index: 165

Text #8

Max Range: 0.1996. Min Range: -0.1996

Max Act: 0.1105. Min Act: -0.0001

Data Index: 1211341 (C4 (Web Text))

Max Activating Token Index: 733

Text #9

Max Range: 0.1996. Min Range: -0.1996

Max Act: 0.1252. Min Act: -0.0001

Data Index: 640416 (C4 (Web Text))

Max Activating Token Index: 354

Text #10

Max Range: 0.1996. Min Range: -0.1996

Max Act: 0.1128. Min Act: -0.0001

Data Index: 327841 (C4 (Web Text))

Max Activating Token Index: 95

Text #11

Max Range: 0.1996. Min Range: -0.1996

Max Act: 0.1175. Min Act: -0.0001

Data Index: 69347 (C4 (Web Text))

Max Activating Token Index: 599

Text #12

Max Range: 0.1996. Min Range: -0.1996

Max Act: 0.1125. Min Act: -0.0001

Data Index: 739671 (C4 (Web Text))

Max Activating Token Index: 43

Text #13

Max Range: 0.1996. Min Range: -0.1996

Max Act: 0.0958. Min Act: -0.0001

Data Index: 214695 (C4 (Web Text))

Max Activating Token Index: 642

Text #14

Max Range: 0.1996. Min Range: -0.1996

Max Act: 0.0955. Min Act: -0.0001

Data Index: 388901 (C4 (Web Text))

Max Activating Token Index: 937

Text #15

Max Range: 0.1996. Min Range: -0.1996

Max Act: 0.0946. Min Act: -0.0001

Data Index: 91009 (C4 (Web Text))

Max Activating Token Index: 851

Text #16

Max Range: 0.1996. Min Range: -0.1996

Max Act: 0.1138. Min Act: -0.0001

Data Index: 745990 (C4 (Web Text))

Max Activating Token Index: 621

Text #17

Max Range: 0.1996. Min Range: -0.1996

Max Act: 0.1071. Min Act: -0.0001

Data Index: 151053 (C4 (Web Text))

Max Activating Token Index: 327

Text #18

Max Range: 0.1996. Min Range: -0.1996

Max Act: 0.1085. Min Act: -0.0001

Data Index: 152093 (C4 (Web Text))

Max Activating Token Index: 870

Text #19

Max Range: 0.1996. Min Range: -0.1996

Max Act: 0.1005. Min Act: -0.0001

Data Index: 82495 (C4 (Web Text))

Max Activating Token Index: 422