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

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

Neuron 1894 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: 0.1310. Min Range: -0.1310

Max Act: 0.1310. Min Act: -0.0002

Data Index: 1003600 (C4 (Web Text))

Max Activating Token Index: 89

Text #1

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.1081. Min Act: -0.0002

Data Index: 403099 (C4 (Web Text))

Max Activating Token Index: 356

Text #2

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.0970. Min Act: -0.0002

Data Index: 86122 (C4 (Web Text))

Max Activating Token Index: 225

Text #3

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.0976. Min Act: -0.0002

Data Index: 676748 (C4 (Web Text))

Max Activating Token Index: 187

Text #4

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.0904. Min Act: -0.0002

Data Index: 557729 (C4 (Web Text))

Max Activating Token Index: 308

Text #5

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.0892. Min Act: -0.0002

Data Index: 1220375 (C4 (Web Text))

Max Activating Token Index: 18

Text #6

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.0954. Min Act: -0.0002

Data Index: 497921 (C4 (Web Text))

Max Activating Token Index: 168

Text #7

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.0905. Min Act: -0.0002

Data Index: 689376 (C4 (Web Text))

Max Activating Token Index: 103

Text #8

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.0891. Min Act: -0.0002

Data Index: 227029 (C4 (Web Text))

Max Activating Token Index: 422

Text #9

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.0852. Min Act: -0.0002

Data Index: 749200 (C4 (Web Text))

Max Activating Token Index: 196

Text #10

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.0873. Min Act: -0.0002

Data Index: 95049 (C4 (Web Text))

Max Activating Token Index: 518

Text #11

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.0840. Min Act: -0.0002

Data Index: 554888 (C4 (Web Text))

Max Activating Token Index: 389

Text #12

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.0804. Min Act: -0.0002

Data Index: 1278013 (C4 (Web Text))

Max Activating Token Index: 226

Text #13

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.0863. Min Act: -0.0002

Data Index: 747789 (C4 (Web Text))

Max Activating Token Index: 670

Text #14

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.0818. Min Act: -0.0002

Data Index: 832170 (C4 (Web Text))

Max Activating Token Index: 35

Text #15

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.0814. Min Act: -0.0002

Data Index: 1169682 (C4 (Web Text))

Max Activating Token Index: 202

Text #16

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.0845. Min Act: -0.0002

Data Index: 101658 (C4 (Web Text))

Max Activating Token Index: 216

Text #17

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.0780. Min Act: -0.0002

Data Index: 768301 (C4 (Web Text))

Max Activating Token Index: 126

Text #18

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.0832. Min Act: -0.0002

Data Index: 784060 (C4 (Web Text))

Max Activating Token Index: 60

Text #19

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.0798. Min Act: -0.0002

Data Index: 980247 (C4 (Web Text))

Max Activating Token Index: 561