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

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

Neuron 2758 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0955. Min Act: -0.0000

Data Index: 147253 (C4 (Web Text))

Max Activating Token Index: 772

Text #1

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0917. Min Act: -0.0000

Data Index: 1340511 (C4 (Web Text))

Max Activating Token Index: 999

Text #2

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0964. Min Act: -0.0000

Data Index: 685931 (C4 (Web Text))

Max Activating Token Index: 655

Text #3

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0894. Min Act: -0.0000

Data Index: 1250017 (C4 (Web Text))

Max Activating Token Index: 301

Text #4

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0933. Min Act: -0.0000

Data Index: 529827 (C4 (Web Text))

Max Activating Token Index: 96

Text #5

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0967. Min Act: -0.0001

Data Index: 775294 (C4 (Web Text))

Max Activating Token Index: 1021

Text #6

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0891. Min Act: -0.0000

Data Index: 725103 (C4 (Web Text))

Max Activating Token Index: 407

Text #7

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0872. Min Act: -0.0000

Data Index: 175635 (C4 (Web Text))

Max Activating Token Index: 412

Text #8

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0871. Min Act: -0.0000

Data Index: 1069090 (C4 (Web Text))

Max Activating Token Index: 948

Text #9

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0814. Min Act: -0.0000

Data Index: 159257 (C4 (Web Text))

Max Activating Token Index: 915

Text #10

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0827. Min Act: -0.0000

Data Index: 1190274 (C4 (Web Text))

Max Activating Token Index: 389

Text #11

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0888. Min Act: -0.0000

Data Index: 1006635 (C4 (Web Text))

Max Activating Token Index: 140

Text #12

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0832. Min Act: -0.0000

Data Index: 17872 (C4 (Web Text))

Max Activating Token Index: 647

Text #13

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0885. Min Act: -0.0000

Data Index: 127160 (C4 (Web Text))

Max Activating Token Index: 902

Text #14

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0759. Min Act: -0.0000

Data Index: 5543 (C4 (Web Text))

Max Activating Token Index: 73

Text #15

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0809. Min Act: -0.0000

Data Index: 885129 (C4 (Web Text))

Max Activating Token Index: 738

Text #16

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0844. Min Act: -0.0000

Data Index: 78070 (C4 (Web Text))

Max Activating Token Index: 255

Text #17

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0848. Min Act: -0.0000

Data Index: 219738 (C4 (Web Text))

Max Activating Token Index: 152

Text #18

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0803. Min Act: -0.0000

Data Index: 829342 (C4 (Web Text))

Max Activating Token Index: 278

Text #19

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0773. Min Act: -0.0000

Data Index: 439566 (C4 (Web Text))

Max Activating Token Index: 946