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

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

Neuron 4147 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0929. Min Act: -0.0002

Data Index: 1282851 (C4 (Web Text))

Max Activating Token Index: 361

Text #1

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0793. Min Act: -0.0002

Data Index: 1195080 (C4 (Web Text))

Max Activating Token Index: 546

Text #2

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0757. Min Act: -0.0002

Data Index: 751399 (C4 (Web Text))

Max Activating Token Index: 413

Text #3

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0811. Min Act: -0.0002

Data Index: 74847 (C4 (Web Text))

Max Activating Token Index: 479

Text #4

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0755. Min Act: -0.0002

Data Index: 309672 (C4 (Web Text))

Max Activating Token Index: 190

Text #5

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0779. Min Act: -0.0002

Data Index: 974568 (C4 (Web Text))

Max Activating Token Index: 324

Text #6

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0801. Min Act: -0.0002

Data Index: 17616 (C4 (Web Text))

Max Activating Token Index: 37

Text #7

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0761. Min Act: -0.0002

Data Index: 822974 (C4 (Web Text))

Max Activating Token Index: 749

Text #8

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0713. Min Act: -0.0002

Data Index: 921726 (C4 (Web Text))

Max Activating Token Index: 150

Text #9

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0621. Min Act: -0.0002

Data Index: 1331393 (C4 (Web Text))

Max Activating Token Index: 349

Text #10

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0515. Min Act: -0.0002

Data Index: 1117249 (C4 (Web Text))

Max Activating Token Index: 233

Text #11

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0717. Min Act: -0.0002

Data Index: 1254629 (C4 (Web Text))

Max Activating Token Index: 794

Text #12

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0644. Min Act: -0.0002

Data Index: 296943 (C4 (Web Text))

Max Activating Token Index: 853

Text #13

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0630. Min Act: -0.0002

Data Index: 816476 (C4 (Web Text))

Max Activating Token Index: 142

Text #14

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0693. Min Act: -0.0002

Data Index: 434972 (C4 (Web Text))

Max Activating Token Index: 981

Text #15

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0661. Min Act: -0.0002

Data Index: 173439 (C4 (Web Text))

Max Activating Token Index: 432

Text #16

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0743. Min Act: -0.0002

Data Index: 360757 (C4 (Web Text))

Max Activating Token Index: 574

Text #17

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0643. Min Act: -0.0002

Data Index: 526610 (C4 (Web Text))

Max Activating Token Index: 268

Text #18

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0682. Min Act: -0.0002

Data Index: 452785 (C4 (Web Text))

Max Activating Token Index: 19

Text #19

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0731. Min Act: -0.0002

Data Index: 555220 (C4 (Web Text))

Max Activating Token Index: 386