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

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

Neuron 3607 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: 0.1311. Min Range: -0.1311

Max Act: 0.1311. Min Act: -0.0000

Data Index: 649529 (C4 (Web Text))

Max Activating Token Index: 503

Text #1

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.1168. Min Act: -0.0000

Data Index: 48139 (C4 (Web Text))

Max Activating Token Index: 490

Text #2

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.1003. Min Act: -0.0000

Data Index: 188883 (C4 (Web Text))

Max Activating Token Index: 574

Text #3

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.0924. Min Act: -0.0001

Data Index: 216585 (C4 (Web Text))

Max Activating Token Index: 339

Text #4

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.0986. Min Act: -0.0000

Data Index: 1292716 (C4 (Web Text))

Max Activating Token Index: 925

Text #5

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.0873. Min Act: -0.0000

Data Index: 601500 (C4 (Web Text))

Max Activating Token Index: 914

Text #6

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.0870. Min Act: -0.0000

Data Index: 1082642 (C4 (Web Text))

Max Activating Token Index: 127

Text #7

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.0881. Min Act: -0.0001

Data Index: 199125 (C4 (Web Text))

Max Activating Token Index: 914

Text #8

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.0893. Min Act: -0.0000

Data Index: 1006158 (C4 (Web Text))

Max Activating Token Index: 357

Text #9

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.0890. Min Act: -0.0000

Data Index: 1288501 (C4 (Web Text))

Max Activating Token Index: 798

Text #10

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.0827. Min Act: -0.0000

Data Index: 805560 (C4 (Web Text))

Max Activating Token Index: 615

Text #11

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.0865. Min Act: -0.0000

Data Index: 550151 (C4 (Web Text))

Max Activating Token Index: 645

Text #12

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.0752. Min Act: -0.0000

Data Index: 735585 (C4 (Web Text))

Max Activating Token Index: 783

Text #13

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.0766. Min Act: -0.0000

Data Index: 1086463 (C4 (Web Text))

Max Activating Token Index: 557

Text #14

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.0790. Min Act: -0.0000

Data Index: 552566 (C4 (Web Text))

Max Activating Token Index: 454

Text #15

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.0798. Min Act: -0.0000

Data Index: 1037061 (C4 (Web Text))

Max Activating Token Index: 548

Text #16

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.0830. Min Act: -0.0000

Data Index: 1116454 (C4 (Web Text))

Max Activating Token Index: 630

Text #17

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.0722. Min Act: -0.0000

Data Index: 815271 (C4 (Web Text))

Max Activating Token Index: 708

Text #18

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.0842. Min Act: -0.0000

Data Index: 513590 (C4 (Web Text))

Max Activating Token Index: 152

Text #19

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.0776. Min Act: -0.0000

Data Index: 245347 (C4 (Web Text))

Max Activating Token Index: 352