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

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

Neuron 3580 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: 0.1007. Min Range: -0.1007

Max Act: 0.1007. Min Act: -0.0000

Data Index: 1038302 (C4 (Web Text))

Max Activating Token Index: 183

Text #1

Max Range: 0.1007. Min Range: -0.1007

Max Act: 0.0906. Min Act: -0.0000

Data Index: 305977 (C4 (Web Text))

Max Activating Token Index: 463

Text #2

Max Range: 0.1007. Min Range: -0.1007

Max Act: 0.0889. Min Act: -0.0000

Data Index: 140566 (C4 (Web Text))

Max Activating Token Index: 978

Text #3

Max Range: 0.1007. Min Range: -0.1007

Max Act: 0.0847. Min Act: -0.0000

Data Index: 1591772 (Python Code)

Max Activating Token Index: 959

Text #4

Max Range: 0.1007. Min Range: -0.1007

Max Act: 0.0803. Min Act: -0.0000

Data Index: 1192597 (C4 (Web Text))

Max Activating Token Index: 309

Text #5

Max Range: 0.1007. Min Range: -0.1007

Max Act: 0.0821. Min Act: -0.0000

Data Index: 15092 (C4 (Web Text))

Max Activating Token Index: 484

Text #6

Max Range: 0.1007. Min Range: -0.1007

Max Act: 0.0776. Min Act: -0.0000

Data Index: 1130453 (C4 (Web Text))

Max Activating Token Index: 215

Text #7

Max Range: 0.1007. Min Range: -0.1007

Max Act: 0.0739. Min Act: -0.0000

Data Index: 63200 (C4 (Web Text))

Max Activating Token Index: 1016

Text #8

Max Range: 0.1007. Min Range: -0.1007

Max Act: 0.0711. Min Act: -0.0000

Data Index: 776916 (C4 (Web Text))

Max Activating Token Index: 798

Text #9

Max Range: 0.1007. Min Range: -0.1007

Max Act: 0.0689. Min Act: -0.0000

Data Index: 601287 (C4 (Web Text))

Max Activating Token Index: 440

Text #10

Max Range: 0.1007. Min Range: -0.1007

Max Act: 0.0705. Min Act: -0.0001

Data Index: 1405917 (Python Code)

Max Activating Token Index: 180

Text #11

Max Range: 0.1007. Min Range: -0.1007

Max Act: 0.0726. Min Act: -0.0000

Data Index: 856890 (C4 (Web Text))

Max Activating Token Index: 472

Text #12

Max Range: 0.1007. Min Range: -0.1007

Max Act: 0.0696. Min Act: -0.0000

Data Index: 1088435 (C4 (Web Text))

Max Activating Token Index: 966

Text #13

Max Range: 0.1007. Min Range: -0.1007

Max Act: 0.0705. Min Act: -0.0000

Data Index: 1546008 (Python Code)

Max Activating Token Index: 759

Text #14

Max Range: 0.1007. Min Range: -0.1007

Max Act: 0.0716. Min Act: -0.0000

Data Index: 359775 (C4 (Web Text))

Max Activating Token Index: 891

Text #15

Max Range: 0.1007. Min Range: -0.1007

Max Act: 0.0716. Min Act: -0.0000

Data Index: 1254488 (C4 (Web Text))

Max Activating Token Index: 809

Text #16

Max Range: 0.1007. Min Range: -0.1007

Max Act: 0.0668. Min Act: -0.0000

Data Index: 1288703 (C4 (Web Text))

Max Activating Token Index: 38

Text #17

Max Range: 0.1007. Min Range: -0.1007

Max Act: 0.0692. Min Act: -0.0000

Data Index: 1237127 (C4 (Web Text))

Max Activating Token Index: 809

Text #18

Max Range: 0.1007. Min Range: -0.1007

Max Act: 0.0702. Min Act: -0.0001

Data Index: 1565704 (Python Code)

Max Activating Token Index: 369

Text #19

Max Range: 0.1007. Min Range: -0.1007

Max Act: 0.0659. Min Act: -0.0000

Data Index: 93121 (C4 (Web Text))

Max Activating Token Index: 492