Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 527 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.1020. Min Range: -0.1020

Max Act: 0.1001. Min Act: -0.0003

Data Index: 321236 (C4 (Web Text))

Max Activating Token Index: 201

Text #1

Max Range: 0.1020. Min Range: -0.1020

Max Act: 0.1020. Min Act: -0.0003

Data Index: 558124 (C4 (Web Text))

Max Activating Token Index: 869

Text #2

Max Range: 0.1020. Min Range: -0.1020

Max Act: 0.0913. Min Act: -0.0003

Data Index: 1311484 (C4 (Web Text))

Max Activating Token Index: 177

Text #3

Max Range: 0.1020. Min Range: -0.1020

Max Act: 0.0881. Min Act: -0.0003

Data Index: 1002147 (C4 (Web Text))

Max Activating Token Index: 834

Text #4

Max Range: 0.1020. Min Range: -0.1020

Max Act: 0.0907. Min Act: -0.0003

Data Index: 1073882 (C4 (Web Text))

Max Activating Token Index: 157

Text #5

Max Range: 0.1020. Min Range: -0.1020

Max Act: 0.0885. Min Act: -0.0003

Data Index: 982511 (C4 (Web Text))

Max Activating Token Index: 352

Text #6

Max Range: 0.1020. Min Range: -0.1020

Max Act: 0.0910. Min Act: -0.0003

Data Index: 866671 (C4 (Web Text))

Max Activating Token Index: 178

Text #7

Max Range: 0.1020. Min Range: -0.1020

Max Act: 0.0866. Min Act: -0.0003

Data Index: 773591 (C4 (Web Text))

Max Activating Token Index: 989

Text #8

Max Range: 0.1020. Min Range: -0.1020

Max Act: 0.0874. Min Act: -0.0003

Data Index: 867575 (C4 (Web Text))

Max Activating Token Index: 782

Text #9

Max Range: 0.1020. Min Range: -0.1020

Max Act: 0.0876. Min Act: -0.0003

Data Index: 573044 (C4 (Web Text))

Max Activating Token Index: 1008

Text #10

Max Range: 0.1020. Min Range: -0.1020

Max Act: 0.0851. Min Act: -0.0003

Data Index: 659714 (C4 (Web Text))

Max Activating Token Index: 86

Text #11

Max Range: 0.1020. Min Range: -0.1020

Max Act: 0.0862. Min Act: -0.0003

Data Index: 1195581 (C4 (Web Text))

Max Activating Token Index: 892

Text #12

Max Range: 0.1020. Min Range: -0.1020

Max Act: 0.0920. Min Act: -0.0003

Data Index: 266288 (C4 (Web Text))

Max Activating Token Index: 283

Text #13

Max Range: 0.1020. Min Range: -0.1020

Max Act: 0.0843. Min Act: -0.0003

Data Index: 192382 (C4 (Web Text))

Max Activating Token Index: 840

Text #14

Max Range: 0.1020. Min Range: -0.1020

Max Act: 0.0834. Min Act: -0.0003

Data Index: 1190354 (C4 (Web Text))

Max Activating Token Index: 132

Text #15

Max Range: 0.1020. Min Range: -0.1020

Max Act: 0.0858. Min Act: -0.0003

Data Index: 868463 (C4 (Web Text))

Max Activating Token Index: 730

Text #16

Max Range: 0.1020. Min Range: -0.1020

Max Act: 0.0858. Min Act: -0.0002

Data Index: 125113 (C4 (Web Text))

Max Activating Token Index: 68

Text #17

Max Range: 0.1020. Min Range: -0.1020

Max Act: 0.0768. Min Act: -0.0003

Data Index: 928814 (C4 (Web Text))

Max Activating Token Index: 732

Text #18

Max Range: 0.1020. Min Range: -0.1020

Max Act: 0.0860. Min Act: -0.0003

Data Index: 411339 (C4 (Web Text))

Max Activating Token Index: 341

Text #19

Max Range: 0.1020. Min Range: -0.1020

Max Act: 0.0853. Min Act: -0.0003

Data Index: 1007385 (C4 (Web Text))

Max Activating Token Index: 827