Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 4054 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0948. Min Act: -0.0002

Data Index: 1270653 (C4 (Web Text))

Max Activating Token Index: 955

Text #1

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0936. Min Act: -0.0002

Data Index: 698765 (C4 (Web Text))

Max Activating Token Index: 57

Text #2

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0908. Min Act: -0.0002

Data Index: 51112 (C4 (Web Text))

Max Activating Token Index: 377

Text #3

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0940. Min Act: -0.0001

Data Index: 1126317 (C4 (Web Text))

Max Activating Token Index: 732

Text #4

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0894. Min Act: -0.0002

Data Index: 1008588 (C4 (Web Text))

Max Activating Token Index: 727

Text #5

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0867. Min Act: -0.0002

Data Index: 814 (C4 (Web Text))

Max Activating Token Index: 918

Text #6

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0862. Min Act: -0.0002

Data Index: 1276415 (C4 (Web Text))

Max Activating Token Index: 937

Text #7

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0880. Min Act: -0.0001

Data Index: 723149 (C4 (Web Text))

Max Activating Token Index: 492

Text #8

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0851. Min Act: -0.0001

Data Index: 792181 (C4 (Web Text))

Max Activating Token Index: 603

Text #9

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0899. Min Act: -0.0002

Data Index: 409969 (C4 (Web Text))

Max Activating Token Index: 698

Text #10

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0835. Min Act: -0.0002

Data Index: 561733 (C4 (Web Text))

Max Activating Token Index: 891

Text #11

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0856. Min Act: -0.0002

Data Index: 227500 (C4 (Web Text))

Max Activating Token Index: 752

Text #12

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0792. Min Act: -0.0002

Data Index: 1290357 (C4 (Web Text))

Max Activating Token Index: 578

Text #13

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0815. Min Act: -0.0001

Data Index: 1229909 (C4 (Web Text))

Max Activating Token Index: 792

Text #14

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0844. Min Act: -0.0001

Data Index: 1512706 (Python Code)

Max Activating Token Index: 643

Text #15

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0811. Min Act: -0.0002

Data Index: 485525 (C4 (Web Text))

Max Activating Token Index: 717

Text #16

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0807. Min Act: -0.0002

Data Index: 274151 (C4 (Web Text))

Max Activating Token Index: 58

Text #17

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0804. Min Act: -0.0002

Data Index: 216055 (C4 (Web Text))

Max Activating Token Index: 165

Text #18

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0824. Min Act: -0.0002

Data Index: 835500 (C4 (Web Text))

Max Activating Token Index: 764

Text #19

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0845. Min Act: -0.0002

Data Index: 1353425 (C4 (Web Text))

Max Activating Token Index: 169