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

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

Neuron 4314 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: 0.0831. Min Range: -0.0831

Max Act: 0.0802. Min Act: -0.0002

Data Index: 292143 (C4 (Web Text))

Max Activating Token Index: 226

Text #1

Max Range: 0.0831. Min Range: -0.0831

Max Act: 0.0772. Min Act: -0.0002

Data Index: 594873 (C4 (Web Text))

Max Activating Token Index: 270

Text #2

Max Range: 0.0831. Min Range: -0.0831

Max Act: 0.0826. Min Act: -0.0002

Data Index: 323620 (C4 (Web Text))

Max Activating Token Index: 38

Text #3

Max Range: 0.0831. Min Range: -0.0831

Max Act: 0.0831. Min Act: -0.0002

Data Index: 659989 (C4 (Web Text))

Max Activating Token Index: 651

Text #4

Max Range: 0.0831. Min Range: -0.0831

Max Act: 0.0769. Min Act: -0.0002

Data Index: 803384 (C4 (Web Text))

Max Activating Token Index: 404

Text #5

Max Range: 0.0831. Min Range: -0.0831

Max Act: 0.0694. Min Act: -0.0002

Data Index: 441068 (C4 (Web Text))

Max Activating Token Index: 837

Text #6

Max Range: 0.0831. Min Range: -0.0831

Max Act: 0.0695. Min Act: -0.0002

Data Index: 958618 (C4 (Web Text))

Max Activating Token Index: 871

Text #7

Max Range: 0.0831. Min Range: -0.0831

Max Act: 0.0695. Min Act: -0.0002

Data Index: 405419 (C4 (Web Text))

Max Activating Token Index: 642

Text #8

Max Range: 0.0831. Min Range: -0.0831

Max Act: 0.0697. Min Act: -0.0002

Data Index: 428348 (C4 (Web Text))

Max Activating Token Index: 997

Text #9

Max Range: 0.0831. Min Range: -0.0831

Max Act: 0.0696. Min Act: -0.0002

Data Index: 97217 (C4 (Web Text))

Max Activating Token Index: 3

Text #10

Max Range: 0.0831. Min Range: -0.0831

Max Act: 0.0691. Min Act: -0.0002

Data Index: 708753 (C4 (Web Text))

Max Activating Token Index: 92

Text #11

Max Range: 0.0831. Min Range: -0.0831

Max Act: 0.0642. Min Act: -0.0002

Data Index: 809353 (C4 (Web Text))

Max Activating Token Index: 65

Text #12

Max Range: 0.0831. Min Range: -0.0831

Max Act: 0.0682. Min Act: -0.0002

Data Index: 1108149 (C4 (Web Text))

Max Activating Token Index: 933

Text #13

Max Range: 0.0831. Min Range: -0.0831

Max Act: 0.0664. Min Act: -0.0002

Data Index: 628576 (C4 (Web Text))

Max Activating Token Index: 143

Text #14

Max Range: 0.0831. Min Range: -0.0831

Max Act: 0.0726. Min Act: -0.0002

Data Index: 889235 (C4 (Web Text))

Max Activating Token Index: 127

Text #15

Max Range: 0.0831. Min Range: -0.0831

Max Act: 0.0719. Min Act: -0.0002

Data Index: 252102 (C4 (Web Text))

Max Activating Token Index: 872

Text #16

Max Range: 0.0831. Min Range: -0.0831

Max Act: 0.0692. Min Act: -0.0002

Data Index: 679305 (C4 (Web Text))

Max Activating Token Index: 28

Text #17

Max Range: 0.0831. Min Range: -0.0831

Max Act: 0.0665. Min Act: -0.0002

Data Index: 290806 (C4 (Web Text))

Max Activating Token Index: 647

Text #18

Max Range: 0.0831. Min Range: -0.0831

Max Act: 0.0719. Min Act: -0.0002

Data Index: 47657 (C4 (Web Text))

Max Activating Token Index: 190

Text #19

Max Range: 0.0831. Min Range: -0.0831

Max Act: 0.0661. Min Act: -0.0002

Data Index: 986075 (C4 (Web Text))

Max Activating Token Index: 534