Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 63 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1061. Min Range: -0.1061

Max Act: 0.1008. Min Act: -0.0002

Data Index: 116446 (C4 (Web Text))

Max Activating Token Index: 75

Text #1

Max Range: 0.1061. Min Range: -0.1061

Max Act: 0.0934. Min Act: -0.0002

Data Index: 998809 (C4 (Web Text))

Max Activating Token Index: 182

Text #2

Max Range: 0.1061. Min Range: -0.1061

Max Act: 0.1061. Min Act: -0.0002

Data Index: 1024012 (C4 (Web Text))

Max Activating Token Index: 176

Text #3

Max Range: 0.1061. Min Range: -0.1061

Max Act: 0.0893. Min Act: -0.0002

Data Index: 1144434 (C4 (Web Text))

Max Activating Token Index: 114

Text #4

Max Range: 0.1061. Min Range: -0.1061

Max Act: 0.0894. Min Act: -0.0002

Data Index: 373332 (C4 (Web Text))

Max Activating Token Index: 343

Text #5

Max Range: 0.1061. Min Range: -0.1061

Max Act: 0.0918. Min Act: -0.0002

Data Index: 471308 (C4 (Web Text))

Max Activating Token Index: 181

Text #6

Max Range: 0.1061. Min Range: -0.1061

Max Act: 0.0911. Min Act: -0.0002

Data Index: 1041519 (C4 (Web Text))

Max Activating Token Index: 66

Text #7

Max Range: 0.1061. Min Range: -0.1061

Max Act: 0.0973. Min Act: -0.0002

Data Index: 369574 (C4 (Web Text))

Max Activating Token Index: 880

Text #8

Max Range: 0.1061. Min Range: -0.1061

Max Act: 0.0962. Min Act: -0.0002

Data Index: 1008476 (C4 (Web Text))

Max Activating Token Index: 310

Text #9

Max Range: 0.1061. Min Range: -0.1061

Max Act: 0.0930. Min Act: -0.0002

Data Index: 1194792 (C4 (Web Text))

Max Activating Token Index: 999

Text #10

Max Range: 0.1061. Min Range: -0.1061

Max Act: 0.0828. Min Act: -0.0002

Data Index: 953950 (C4 (Web Text))

Max Activating Token Index: 806

Text #11

Max Range: 0.1061. Min Range: -0.1061

Max Act: 0.0915. Min Act: -0.0002

Data Index: 203798 (C4 (Web Text))

Max Activating Token Index: 155

Text #12

Max Range: 0.1061. Min Range: -0.1061

Max Act: 0.0841. Min Act: -0.0002

Data Index: 1343956 (C4 (Web Text))

Max Activating Token Index: 827

Text #13

Max Range: 0.1061. Min Range: -0.1061

Max Act: 0.0868. Min Act: -0.0002

Data Index: 1042186 (C4 (Web Text))

Max Activating Token Index: 19

Text #14

Max Range: 0.1061. Min Range: -0.1061

Max Act: 0.0926. Min Act: -0.0002

Data Index: 1206713 (C4 (Web Text))

Max Activating Token Index: 822

Text #15

Max Range: 0.1061. Min Range: -0.1061

Max Act: 0.0924. Min Act: -0.0002

Data Index: 1106501 (C4 (Web Text))

Max Activating Token Index: 840

Text #16

Max Range: 0.1061. Min Range: -0.1061

Max Act: 0.0890. Min Act: -0.0002

Data Index: 1044068 (C4 (Web Text))

Max Activating Token Index: 446

Text #17

Max Range: 0.1061. Min Range: -0.1061

Max Act: 0.0864. Min Act: -0.0002

Data Index: 1268933 (C4 (Web Text))

Max Activating Token Index: 412

Text #18

Max Range: 0.1061. Min Range: -0.1061

Max Act: 0.0847. Min Act: -0.0002

Data Index: 858725 (C4 (Web Text))

Max Activating Token Index: 76

Text #19

Max Range: 0.1061. Min Range: -0.1061

Max Act: 0.0852. Min Act: -0.0002

Data Index: 885036 (C4 (Web Text))

Max Activating Token Index: 20