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

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

Neuron 4439 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5616. Min Range: -0.5616

Max Act: 0.5616. Min Act: -0.0000

Data Index: 22970 (C4 (Web Text))

Max Activating Token Index: 509

Text #1

Max Range: 0.5616. Min Range: -0.5616

Max Act: 0.4899. Min Act: -0.0000

Data Index: 900516 (C4 (Web Text))

Max Activating Token Index: 146

Text #2

Max Range: 0.5616. Min Range: -0.5616

Max Act: 0.4962. Min Act: -0.0000

Data Index: 931017 (C4 (Web Text))

Max Activating Token Index: 248

Text #3

Max Range: 0.5616. Min Range: -0.5616

Max Act: 0.4432. Min Act: -0.0000

Data Index: 1316439 (C4 (Web Text))

Max Activating Token Index: 463

Text #4

Max Range: 0.5616. Min Range: -0.5616

Max Act: 0.3843. Min Act: -0.0000

Data Index: 724206 (C4 (Web Text))

Max Activating Token Index: 826

Text #5

Max Range: 0.5616. Min Range: -0.5616

Max Act: 0.4082. Min Act: -0.0000

Data Index: 27120 (C4 (Web Text))

Max Activating Token Index: 806

Text #6

Max Range: 0.5616. Min Range: -0.5616

Max Act: 0.4160. Min Act: -0.0000

Data Index: 1266547 (C4 (Web Text))

Max Activating Token Index: 734

Text #7

Max Range: 0.5616. Min Range: -0.5616

Max Act: 0.3932. Min Act: -0.0000

Data Index: 38812 (C4 (Web Text))

Max Activating Token Index: 51

Text #8

Max Range: 0.5616. Min Range: -0.5616

Max Act: 0.3907. Min Act: -0.0000

Data Index: 272901 (C4 (Web Text))

Max Activating Token Index: 417

Text #9

Max Range: 0.5616. Min Range: -0.5616

Max Act: 0.3748. Min Act: -0.0000

Data Index: 1267667 (C4 (Web Text))

Max Activating Token Index: 121

Text #10

Max Range: 0.5616. Min Range: -0.5616

Max Act: 0.3955. Min Act: -0.0000

Data Index: 1338783 (C4 (Web Text))

Max Activating Token Index: 193

Text #11

Max Range: 0.5616. Min Range: -0.5616

Max Act: 0.3824. Min Act: -0.0000

Data Index: 1351424 (C4 (Web Text))

Max Activating Token Index: 805

Text #12

Max Range: 0.5616. Min Range: -0.5616

Max Act: 0.3754. Min Act: -0.0000

Data Index: 1238526 (C4 (Web Text))

Max Activating Token Index: 633

Text #13

Max Range: 0.5616. Min Range: -0.5616

Max Act: 0.3490. Min Act: -0.0000

Data Index: 1238998 (C4 (Web Text))

Max Activating Token Index: 178

Text #14

Max Range: 0.5616. Min Range: -0.5616

Max Act: 0.3959. Min Act: -0.0000

Data Index: 135243 (C4 (Web Text))

Max Activating Token Index: 730

Text #15

Max Range: 0.5616. Min Range: -0.5616

Max Act: 0.3689. Min Act: -0.0000

Data Index: 1074073 (C4 (Web Text))

Max Activating Token Index: 421

Text #16

Max Range: 0.5616. Min Range: -0.5616

Max Act: 0.3619. Min Act: -0.0000

Data Index: 715443 (C4 (Web Text))

Max Activating Token Index: 286

Text #17

Max Range: 0.5616. Min Range: -0.5616

Max Act: 0.3717. Min Act: -0.0000

Data Index: 451074 (C4 (Web Text))

Max Activating Token Index: 970

Text #18

Max Range: 0.5616. Min Range: -0.5616

Max Act: 0.3930. Min Act: -0.0000

Data Index: 1123970 (C4 (Web Text))

Max Activating Token Index: 992

Text #19

Max Range: 0.5616. Min Range: -0.5616

Max Act: 0.3456. Min Act: -0.0000

Data Index: 844225 (C4 (Web Text))

Max Activating Token Index: 560