Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3886 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7473. Min Range: -0.7473

Max Act: 0.7406. Min Act: -0.0001

Data Index: 790292 (C4 (Web Text))

Max Activating Token Index: 351

Text #1

Max Range: 0.7473. Min Range: -0.7473

Max Act: 0.7473. Min Act: -0.0002

Data Index: 1197389 (C4 (Web Text))

Max Activating Token Index: 333

Text #2

Max Range: 0.7473. Min Range: -0.7473

Max Act: 0.6871. Min Act: -0.0001

Data Index: 816968 (C4 (Web Text))

Max Activating Token Index: 983

Text #3

Max Range: 0.7473. Min Range: -0.7473

Max Act: 0.6619. Min Act: -0.0002

Data Index: 978213 (C4 (Web Text))

Max Activating Token Index: 848

Text #4

Max Range: 0.7473. Min Range: -0.7473

Max Act: 0.7015. Min Act: -0.0001

Data Index: 1170148 (C4 (Web Text))

Max Activating Token Index: 473

Text #5

Max Range: 0.7473. Min Range: -0.7473

Max Act: 0.6418. Min Act: -0.0001

Data Index: 1008956 (C4 (Web Text))

Max Activating Token Index: 953

Text #6

Max Range: 0.7473. Min Range: -0.7473

Max Act: 0.6887. Min Act: -0.0002

Data Index: 1040890 (C4 (Web Text))

Max Activating Token Index: 998

Text #7

Max Range: 0.7473. Min Range: -0.7473

Max Act: 0.6640. Min Act: -0.0001

Data Index: 319159 (C4 (Web Text))

Max Activating Token Index: 540

Text #8

Max Range: 0.7473. Min Range: -0.7473

Max Act: 0.6904. Min Act: -0.0002

Data Index: 1038266 (C4 (Web Text))

Max Activating Token Index: 896

Text #9

Max Range: 0.7473. Min Range: -0.7473

Max Act: 0.6752. Min Act: -0.0001

Data Index: 738089 (C4 (Web Text))

Max Activating Token Index: 394

Text #10

Max Range: 0.7473. Min Range: -0.7473

Max Act: 0.6072. Min Act: -0.0001

Data Index: 967121 (C4 (Web Text))

Max Activating Token Index: 1000

Text #11

Max Range: 0.7473. Min Range: -0.7473

Max Act: 0.6706. Min Act: -0.0001

Data Index: 370022 (C4 (Web Text))

Max Activating Token Index: 1002

Text #12

Max Range: 0.7473. Min Range: -0.7473

Max Act: 0.6569. Min Act: -0.0001

Data Index: 721728 (C4 (Web Text))

Max Activating Token Index: 228

Text #13

Max Range: 0.7473. Min Range: -0.7473

Max Act: 0.6634. Min Act: -0.0001

Data Index: 962761 (C4 (Web Text))

Max Activating Token Index: 495

Text #14

Max Range: 0.7473. Min Range: -0.7473

Max Act: 0.5978. Min Act: -0.0002

Data Index: 190605 (C4 (Web Text))

Max Activating Token Index: 727

Text #15

Max Range: 0.7473. Min Range: -0.7473

Max Act: 0.6565. Min Act: -0.0002

Data Index: 354447 (C4 (Web Text))

Max Activating Token Index: 800

Text #16

Max Range: 0.7473. Min Range: -0.7473

Max Act: 0.6111. Min Act: -0.0002

Data Index: 1239569 (C4 (Web Text))

Max Activating Token Index: 611

Text #17

Max Range: 0.7473. Min Range: -0.7473

Max Act: 0.6737. Min Act: -0.0001

Data Index: 196067 (C4 (Web Text))

Max Activating Token Index: 343

Text #18

Max Range: 0.7473. Min Range: -0.7473

Max Act: 0.6766. Min Act: -0.0001

Data Index: 1352633 (C4 (Web Text))

Max Activating Token Index: 714

Text #19

Max Range: 0.7473. Min Range: -0.7473

Max Act: 0.6509. Min Act: -0.0001

Data Index: 1146547 (C4 (Web Text))

Max Activating Token Index: 586