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

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

Neuron 1296 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: 0.1079. Min Range: -0.1079

Max Act: 0.1079. Min Act: -0.0001

Data Index: 864199 (C4 (Web Text))

Max Activating Token Index: 71

Text #1

Max Range: 0.1079. Min Range: -0.1079

Max Act: 0.0946. Min Act: -0.0001

Data Index: 1079611 (C4 (Web Text))

Max Activating Token Index: 79

Text #2

Max Range: 0.1079. Min Range: -0.1079

Max Act: 0.0971. Min Act: -0.0001

Data Index: 1303114 (C4 (Web Text))

Max Activating Token Index: 875

Text #3

Max Range: 0.1079. Min Range: -0.1079

Max Act: 0.1008. Min Act: -0.0001

Data Index: 327266 (C4 (Web Text))

Max Activating Token Index: 131

Text #4

Max Range: 0.1079. Min Range: -0.1079

Max Act: 0.0932. Min Act: -0.0001

Data Index: 941094 (C4 (Web Text))

Max Activating Token Index: 883

Text #5

Max Range: 0.1079. Min Range: -0.1079

Max Act: 0.0967. Min Act: -0.0001

Data Index: 731112 (C4 (Web Text))

Max Activating Token Index: 773

Text #6

Max Range: 0.1079. Min Range: -0.1079

Max Act: 0.0910. Min Act: -0.0001

Data Index: 534132 (C4 (Web Text))

Max Activating Token Index: 43

Text #7

Max Range: 0.1079. Min Range: -0.1079

Max Act: 0.0925. Min Act: -0.0001

Data Index: 692219 (C4 (Web Text))

Max Activating Token Index: 220

Text #8

Max Range: 0.1079. Min Range: -0.1079

Max Act: 0.0856. Min Act: -0.0001

Data Index: 1249117 (C4 (Web Text))

Max Activating Token Index: 259

Text #9

Max Range: 0.1079. Min Range: -0.1079

Max Act: 0.0888. Min Act: -0.0001

Data Index: 697103 (C4 (Web Text))

Max Activating Token Index: 107

Text #10

Max Range: 0.1079. Min Range: -0.1079

Max Act: 0.0897. Min Act: -0.0001

Data Index: 714472 (C4 (Web Text))

Max Activating Token Index: 315

Text #11

Max Range: 0.1079. Min Range: -0.1079

Max Act: 0.0914. Min Act: -0.0001

Data Index: 806287 (C4 (Web Text))

Max Activating Token Index: 79

Text #12

Max Range: 0.1079. Min Range: -0.1079

Max Act: 0.0886. Min Act: -0.0001

Data Index: 355917 (C4 (Web Text))

Max Activating Token Index: 552

Text #13

Max Range: 0.1079. Min Range: -0.1079

Max Act: 0.0855. Min Act: -0.0001

Data Index: 445662 (C4 (Web Text))

Max Activating Token Index: 71

Text #14

Max Range: 0.1079. Min Range: -0.1079

Max Act: 0.0732. Min Act: -0.0001

Data Index: 1008132 (C4 (Web Text))

Max Activating Token Index: 209

Text #15

Max Range: 0.1079. Min Range: -0.1079

Max Act: 0.0807. Min Act: -0.0001

Data Index: 740980 (C4 (Web Text))

Max Activating Token Index: 439

Text #16

Max Range: 0.1079. Min Range: -0.1079

Max Act: 0.0861. Min Act: -0.0001

Data Index: 833867 (C4 (Web Text))

Max Activating Token Index: 889

Text #17

Max Range: 0.1079. Min Range: -0.1079

Max Act: 0.0897. Min Act: -0.0001

Data Index: 590191 (C4 (Web Text))

Max Activating Token Index: 573

Text #18

Max Range: 0.1079. Min Range: -0.1079

Max Act: 0.0966. Min Act: -0.0001

Data Index: 1184256 (C4 (Web Text))

Max Activating Token Index: 926

Text #19

Max Range: 0.1079. Min Range: -0.1079

Max Act: 0.0828. Min Act: -0.0001

Data Index: 192695 (C4 (Web Text))

Max Activating Token Index: 179