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

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

Neuron 1996 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0945. Min Range: -0.0945

Max Act: 0.0945. Min Act: -0.0006

Data Index: 458670 (C4 (Web Text))

Max Activating Token Index: 34

Text #1

Max Range: 0.0945. Min Range: -0.0945

Max Act: 0.0877. Min Act: -0.0006

Data Index: 327210 (C4 (Web Text))

Max Activating Token Index: 346

Text #2

Max Range: 0.0945. Min Range: -0.0945

Max Act: 0.0794. Min Act: -0.0006

Data Index: 1204332 (C4 (Web Text))

Max Activating Token Index: 194

Text #3

Max Range: 0.0945. Min Range: -0.0945

Max Act: 0.0844. Min Act: -0.0006

Data Index: 50986 (C4 (Web Text))

Max Activating Token Index: 52

Text #4

Max Range: 0.0945. Min Range: -0.0945

Max Act: 0.0799. Min Act: -0.0006

Data Index: 611057 (C4 (Web Text))

Max Activating Token Index: 116

Text #5

Max Range: 0.0945. Min Range: -0.0945

Max Act: 0.0740. Min Act: -0.0006

Data Index: 1215463 (C4 (Web Text))

Max Activating Token Index: 649

Text #6

Max Range: 0.0945. Min Range: -0.0945

Max Act: 0.0787. Min Act: -0.0006

Data Index: 1015480 (C4 (Web Text))

Max Activating Token Index: 37

Text #7

Max Range: 0.0945. Min Range: -0.0945

Max Act: 0.0765. Min Act: -0.0006

Data Index: 1048796 (C4 (Web Text))

Max Activating Token Index: 187

Text #8

Max Range: 0.0945. Min Range: -0.0945

Max Act: 0.0729. Min Act: -0.0006

Data Index: 600300 (C4 (Web Text))

Max Activating Token Index: 29

Text #9

Max Range: 0.0945. Min Range: -0.0945

Max Act: 0.0757. Min Act: -0.0006

Data Index: 1109472 (C4 (Web Text))

Max Activating Token Index: 96

Text #10

Max Range: 0.0945. Min Range: -0.0945

Max Act: 0.0751. Min Act: -0.0006

Data Index: 1135367 (C4 (Web Text))

Max Activating Token Index: 303

Text #11

Max Range: 0.0945. Min Range: -0.0945

Max Act: 0.0742. Min Act: -0.0006

Data Index: 235764 (C4 (Web Text))

Max Activating Token Index: 115

Text #12

Max Range: 0.0945. Min Range: -0.0945

Max Act: 0.0739. Min Act: -0.0006

Data Index: 1314482 (C4 (Web Text))

Max Activating Token Index: 350

Text #13

Max Range: 0.0945. Min Range: -0.0945

Max Act: 0.0755. Min Act: -0.0006

Data Index: 129747 (C4 (Web Text))

Max Activating Token Index: 957

Text #14

Max Range: 0.0945. Min Range: -0.0945

Max Act: 0.0751. Min Act: -0.0006

Data Index: 1281844 (C4 (Web Text))

Max Activating Token Index: 646

Text #15

Max Range: 0.0945. Min Range: -0.0945

Max Act: 0.0717. Min Act: -0.0006

Data Index: 458592 (C4 (Web Text))

Max Activating Token Index: 464

Text #16

Max Range: 0.0945. Min Range: -0.0945

Max Act: 0.0743. Min Act: -0.0006

Data Index: 433437 (C4 (Web Text))

Max Activating Token Index: 49

Text #17

Max Range: 0.0945. Min Range: -0.0945

Max Act: 0.0686. Min Act: -0.0006

Data Index: 96490 (C4 (Web Text))

Max Activating Token Index: 33

Text #18

Max Range: 0.0945. Min Range: -0.0945

Max Act: 0.0713. Min Act: -0.0006

Data Index: 941999 (C4 (Web Text))

Max Activating Token Index: 536

Text #19

Max Range: 0.0945. Min Range: -0.0945

Max Act: 0.0708. Min Act: -0.0006

Data Index: 577263 (C4 (Web Text))

Max Activating Token Index: 47