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

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

Neuron 5838 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.1089. Min Act: -0.0002

Data Index: 1326417 (C4 (Web Text))

Max Activating Token Index: 544

Text #1

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.1016. Min Act: -0.0002

Data Index: 1186449 (C4 (Web Text))

Max Activating Token Index: 455

Text #2

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0989. Min Act: -0.0002

Data Index: 1307105 (C4 (Web Text))

Max Activating Token Index: 313

Text #3

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0972. Min Act: -0.0002

Data Index: 567853 (C4 (Web Text))

Max Activating Token Index: 445

Text #4

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0855. Min Act: -0.0002

Data Index: 568626 (C4 (Web Text))

Max Activating Token Index: 612

Text #5

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0897. Min Act: -0.0002

Data Index: 588706 (C4 (Web Text))

Max Activating Token Index: 952

Text #6

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0853. Min Act: -0.0002

Data Index: 576741 (C4 (Web Text))

Max Activating Token Index: 291

Text #7

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0803. Min Act: -0.0002

Data Index: 470577 (C4 (Web Text))

Max Activating Token Index: 962

Text #8

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0791. Min Act: -0.0002

Data Index: 1347221 (C4 (Web Text))

Max Activating Token Index: 804

Text #9

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0756. Min Act: -0.0002

Data Index: 160388 (C4 (Web Text))

Max Activating Token Index: 245

Text #10

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0756. Min Act: -0.0002

Data Index: 1277891 (C4 (Web Text))

Max Activating Token Index: 191

Text #11

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0751. Min Act: -0.0002

Data Index: 884081 (C4 (Web Text))

Max Activating Token Index: 595

Text #12

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0739. Min Act: -0.0002

Data Index: 519401 (C4 (Web Text))

Max Activating Token Index: 144

Text #13

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0729. Min Act: -0.0002

Data Index: 313779 (C4 (Web Text))

Max Activating Token Index: 10

Text #14

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0728. Min Act: -0.0002

Data Index: 924639 (C4 (Web Text))

Max Activating Token Index: 550

Text #15

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0722. Min Act: -0.0002

Data Index: 434878 (C4 (Web Text))

Max Activating Token Index: 72

Text #16

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0696. Min Act: -0.0002

Data Index: 973283 (C4 (Web Text))

Max Activating Token Index: 154

Text #17

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0728. Min Act: -0.0002

Data Index: 633276 (C4 (Web Text))

Max Activating Token Index: 788

Text #18

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0680. Min Act: -0.0002

Data Index: 870547 (C4 (Web Text))

Max Activating Token Index: 68

Text #19

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0706. Min Act: -0.0002

Data Index: 408778 (C4 (Web Text))

Max Activating Token Index: 67