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

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

Neuron 386 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: 0.1114. Min Range: -0.1114

Max Act: 0.1114. Min Act: -0.0003

Data Index: 194408 (C4 (Web Text))

Max Activating Token Index: 62

Text #1

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.1110. Min Act: -0.0003

Data Index: 1176694 (C4 (Web Text))

Max Activating Token Index: 207

Text #2

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.1054. Min Act: -0.0003

Data Index: 669144 (C4 (Web Text))

Max Activating Token Index: 210

Text #3

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0984. Min Act: -0.0003

Data Index: 919346 (C4 (Web Text))

Max Activating Token Index: 373

Text #4

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0913. Min Act: -0.0003

Data Index: 966585 (C4 (Web Text))

Max Activating Token Index: 371

Text #5

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0874. Min Act: -0.0003

Data Index: 1629 (C4 (Web Text))

Max Activating Token Index: 847

Text #6

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0908. Min Act: -0.0003

Data Index: 914497 (C4 (Web Text))

Max Activating Token Index: 927

Text #7

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0894. Min Act: -0.0003

Data Index: 425167 (C4 (Web Text))

Max Activating Token Index: 758

Text #8

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0885. Min Act: -0.0003

Data Index: 850841 (C4 (Web Text))

Max Activating Token Index: 647

Text #9

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0813. Min Act: -0.0003

Data Index: 197211 (C4 (Web Text))

Max Activating Token Index: 666

Text #10

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0811. Min Act: -0.0003

Data Index: 173119 (C4 (Web Text))

Max Activating Token Index: 650

Text #11

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0841. Min Act: -0.0003

Data Index: 1239143 (C4 (Web Text))

Max Activating Token Index: 722

Text #12

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0801. Min Act: -0.0003

Data Index: 855274 (C4 (Web Text))

Max Activating Token Index: 667

Text #13

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0833. Min Act: -0.0003

Data Index: 1093612 (C4 (Web Text))

Max Activating Token Index: 612

Text #14

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0865. Min Act: -0.0003

Data Index: 717166 (C4 (Web Text))

Max Activating Token Index: 647

Text #15

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0828. Min Act: -0.0003

Data Index: 321002 (C4 (Web Text))

Max Activating Token Index: 569

Text #16

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0810. Min Act: -0.0003

Data Index: 850739 (C4 (Web Text))

Max Activating Token Index: 668

Text #17

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0845. Min Act: -0.0003

Data Index: 709510 (C4 (Web Text))

Max Activating Token Index: 944

Text #18

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0805. Min Act: -0.0003

Data Index: 128135 (C4 (Web Text))

Max Activating Token Index: 906

Text #19

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0792. Min Act: -0.0003

Data Index: 1267377 (C4 (Web Text))

Max Activating Token Index: 619