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

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

Neuron 2694 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: 0.1060. Min Range: -0.1060

Max Act: 0.1060. Min Act: -0.0002

Data Index: 1255013 (C4 (Web Text))

Max Activating Token Index: 734

Text #1

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.1005. Min Act: -0.0001

Data Index: 109880 (C4 (Web Text))

Max Activating Token Index: 119

Text #2

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0993. Min Act: -0.0002

Data Index: 921195 (C4 (Web Text))

Max Activating Token Index: 895

Text #3

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0946. Min Act: -0.0002

Data Index: 1142923 (C4 (Web Text))

Max Activating Token Index: 851

Text #4

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.1011. Min Act: -0.0001

Data Index: 928230 (C4 (Web Text))

Max Activating Token Index: 29

Text #5

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0954. Min Act: -0.0001

Data Index: 847295 (C4 (Web Text))

Max Activating Token Index: 183

Text #6

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.1008. Min Act: -0.0002

Data Index: 690943 (C4 (Web Text))

Max Activating Token Index: 435

Text #7

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.1008. Min Act: -0.0002

Data Index: 1200711 (C4 (Web Text))

Max Activating Token Index: 86

Text #8

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0923. Min Act: -0.0001

Data Index: 661431 (C4 (Web Text))

Max Activating Token Index: 236

Text #9

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0927. Min Act: -0.0002

Data Index: 1152262 (C4 (Web Text))

Max Activating Token Index: 115

Text #10

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0977. Min Act: -0.0002

Data Index: 1018632 (C4 (Web Text))

Max Activating Token Index: 523

Text #11

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0866. Min Act: -0.0002

Data Index: 1183084 (C4 (Web Text))

Max Activating Token Index: 576

Text #12

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0862. Min Act: -0.0002

Data Index: 1244437 (C4 (Web Text))

Max Activating Token Index: 42

Text #13

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0915. Min Act: -0.0002

Data Index: 1100437 (C4 (Web Text))

Max Activating Token Index: 77

Text #14

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0945. Min Act: -0.0002

Data Index: 603827 (C4 (Web Text))

Max Activating Token Index: 75

Text #15

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0883. Min Act: -0.0002

Data Index: 489139 (C4 (Web Text))

Max Activating Token Index: 41

Text #16

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0883. Min Act: -0.0001

Data Index: 1371446 (Python Code)

Max Activating Token Index: 855

Text #17

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0839. Min Act: -0.0002

Data Index: 61792 (C4 (Web Text))

Max Activating Token Index: 769

Text #18

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0878. Min Act: -0.0001

Data Index: 1614850 (Python Code)

Max Activating Token Index: 307

Text #19

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0749. Min Act: -0.0002

Data Index: 1245277 (C4 (Web Text))

Max Activating Token Index: 689