Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 493 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0895. Min Range: -0.0895

Max Act: 0.0858. Min Act: -0.0003

Data Index: 576137 (C4 (Web Text))

Max Activating Token Index: 160

Text #1

Max Range: 0.0895. Min Range: -0.0895

Max Act: 0.0895. Min Act: -0.0003

Data Index: 639492 (C4 (Web Text))

Max Activating Token Index: 784

Text #2

Max Range: 0.0895. Min Range: -0.0895

Max Act: 0.0853. Min Act: -0.0003

Data Index: 284169 (C4 (Web Text))

Max Activating Token Index: 104

Text #3

Max Range: 0.0895. Min Range: -0.0895

Max Act: 0.0836. Min Act: -0.0003

Data Index: 17075 (C4 (Web Text))

Max Activating Token Index: 210

Text #4

Max Range: 0.0895. Min Range: -0.0895

Max Act: 0.0862. Min Act: -0.0003

Data Index: 998928 (C4 (Web Text))

Max Activating Token Index: 292

Text #5

Max Range: 0.0895. Min Range: -0.0895

Max Act: 0.0841. Min Act: -0.0003

Data Index: 38336 (C4 (Web Text))

Max Activating Token Index: 63

Text #6

Max Range: 0.0895. Min Range: -0.0895

Max Act: 0.0789. Min Act: -0.0003

Data Index: 866467 (C4 (Web Text))

Max Activating Token Index: 786

Text #7

Max Range: 0.0895. Min Range: -0.0895

Max Act: 0.0832. Min Act: -0.0003

Data Index: 174824 (C4 (Web Text))

Max Activating Token Index: 891

Text #8

Max Range: 0.0895. Min Range: -0.0895

Max Act: 0.0831. Min Act: -0.0003

Data Index: 1169301 (C4 (Web Text))

Max Activating Token Index: 383

Text #9

Max Range: 0.0895. Min Range: -0.0895

Max Act: 0.0808. Min Act: -0.0003

Data Index: 1220380 (C4 (Web Text))

Max Activating Token Index: 501

Text #10

Max Range: 0.0895. Min Range: -0.0895

Max Act: 0.0808. Min Act: -0.0003

Data Index: 550275 (C4 (Web Text))

Max Activating Token Index: 309

Text #11

Max Range: 0.0895. Min Range: -0.0895

Max Act: 0.0787. Min Act: -0.0003

Data Index: 1066155 (C4 (Web Text))

Max Activating Token Index: 274

Text #12

Max Range: 0.0895. Min Range: -0.0895

Max Act: 0.0797. Min Act: -0.0003

Data Index: 645265 (C4 (Web Text))

Max Activating Token Index: 242

Text #13

Max Range: 0.0895. Min Range: -0.0895

Max Act: 0.0805. Min Act: -0.0003

Data Index: 871065 (C4 (Web Text))

Max Activating Token Index: 228

Text #14

Max Range: 0.0895. Min Range: -0.0895

Max Act: 0.0784. Min Act: -0.0003

Data Index: 691915 (C4 (Web Text))

Max Activating Token Index: 182

Text #15

Max Range: 0.0895. Min Range: -0.0895

Max Act: 0.0783. Min Act: -0.0003

Data Index: 340214 (C4 (Web Text))

Max Activating Token Index: 142

Text #16

Max Range: 0.0895. Min Range: -0.0895

Max Act: 0.0811. Min Act: -0.0003

Data Index: 508041 (C4 (Web Text))

Max Activating Token Index: 170

Text #17

Max Range: 0.0895. Min Range: -0.0895

Max Act: 0.0752. Min Act: -0.0003

Data Index: 1000365 (C4 (Web Text))

Max Activating Token Index: 458

Text #18

Max Range: 0.0895. Min Range: -0.0895

Max Act: 0.0754. Min Act: -0.0003

Data Index: 956582 (C4 (Web Text))

Max Activating Token Index: 280

Text #19

Max Range: 0.0895. Min Range: -0.0895

Max Act: 0.0766. Min Act: -0.0003

Data Index: 697047 (C4 (Web Text))

Max Activating Token Index: 101