Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1586 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0819. Min Range: -0.0819

Max Act: 0.0819. Min Act: -0.0002

Data Index: 48246 (C4 (Web Text))

Max Activating Token Index: 138

Text #1

Max Range: 0.0819. Min Range: -0.0819

Max Act: 0.0686. Min Act: -0.0002

Data Index: 1134714 (C4 (Web Text))

Max Activating Token Index: 201

Text #2

Max Range: 0.0819. Min Range: -0.0819

Max Act: 0.0661. Min Act: -0.0002

Data Index: 806109 (C4 (Web Text))

Max Activating Token Index: 174

Text #3

Max Range: 0.0819. Min Range: -0.0819

Max Act: 0.0636. Min Act: -0.0002

Data Index: 56930 (C4 (Web Text))

Max Activating Token Index: 98

Text #4

Max Range: 0.0819. Min Range: -0.0819

Max Act: 0.0624. Min Act: -0.0002

Data Index: 333229 (C4 (Web Text))

Max Activating Token Index: 98

Text #5

Max Range: 0.0819. Min Range: -0.0819

Max Act: 0.0604. Min Act: -0.0002

Data Index: 759799 (C4 (Web Text))

Max Activating Token Index: 156

Text #6

Max Range: 0.0819. Min Range: -0.0819

Max Act: 0.0619. Min Act: -0.0002

Data Index: 1140388 (C4 (Web Text))

Max Activating Token Index: 66

Text #7

Max Range: 0.0819. Min Range: -0.0819

Max Act: 0.0610. Min Act: -0.0002

Data Index: 367879 (C4 (Web Text))

Max Activating Token Index: 127

Text #8

Max Range: 0.0819. Min Range: -0.0819

Max Act: 0.0607. Min Act: -0.0002

Data Index: 1310225 (C4 (Web Text))

Max Activating Token Index: 101

Text #9

Max Range: 0.0819. Min Range: -0.0819

Max Act: 0.0584. Min Act: -0.0002

Data Index: 502893 (C4 (Web Text))

Max Activating Token Index: 11

Text #10

Max Range: 0.0819. Min Range: -0.0819

Max Act: 0.0600. Min Act: -0.0002

Data Index: 937509 (C4 (Web Text))

Max Activating Token Index: 107

Text #11

Max Range: 0.0819. Min Range: -0.0819

Max Act: 0.0599. Min Act: -0.0002

Data Index: 746626 (C4 (Web Text))

Max Activating Token Index: 201

Text #12

Max Range: 0.0819. Min Range: -0.0819

Max Act: 0.0601. Min Act: -0.0002

Data Index: 885018 (C4 (Web Text))

Max Activating Token Index: 596

Text #13

Max Range: 0.0819. Min Range: -0.0819

Max Act: 0.0596. Min Act: -0.0002

Data Index: 402762 (C4 (Web Text))

Max Activating Token Index: 240

Text #14

Max Range: 0.0819. Min Range: -0.0819

Max Act: 0.0578. Min Act: -0.0002

Data Index: 264089 (C4 (Web Text))

Max Activating Token Index: 261

Text #15

Max Range: 0.0819. Min Range: -0.0819

Max Act: 0.0559. Min Act: -0.0002

Data Index: 803999 (C4 (Web Text))

Max Activating Token Index: 670

Text #16

Max Range: 0.0819. Min Range: -0.0819

Max Act: 0.0579. Min Act: -0.0002

Data Index: 1151668 (C4 (Web Text))

Max Activating Token Index: 124

Text #17

Max Range: 0.0819. Min Range: -0.0819

Max Act: 0.0573. Min Act: -0.0002

Data Index: 177228 (C4 (Web Text))

Max Activating Token Index: 213

Text #18

Max Range: 0.0819. Min Range: -0.0819

Max Act: 0.0569. Min Act: -0.0002

Data Index: 69448 (C4 (Web Text))

Max Activating Token Index: 26

Text #19

Max Range: 0.0819. Min Range: -0.0819

Max Act: 0.0564. Min Act: -0.0002

Data Index: 462496 (C4 (Web Text))

Max Activating Token Index: 596