Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1653 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0802. Min Act: -0.0002

Data Index: 1181880 (C4 (Web Text))

Max Activating Token Index: 956

Text #1

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0824. Min Act: -0.0002

Data Index: 864753 (C4 (Web Text))

Max Activating Token Index: 709

Text #2

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0781. Min Act: -0.0002

Data Index: 348309 (C4 (Web Text))

Max Activating Token Index: 415

Text #3

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0780. Min Act: -0.0002

Data Index: 784521 (C4 (Web Text))

Max Activating Token Index: 574

Text #4

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0769. Min Act: -0.0002

Data Index: 459415 (C4 (Web Text))

Max Activating Token Index: 912

Text #5

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0800. Min Act: -0.0002

Data Index: 318396 (C4 (Web Text))

Max Activating Token Index: 1007

Text #6

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0760. Min Act: -0.0002

Data Index: 1069769 (C4 (Web Text))

Max Activating Token Index: 930

Text #7

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0811. Min Act: -0.0002

Data Index: 9606 (C4 (Web Text))

Max Activating Token Index: 480

Text #8

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0772. Min Act: -0.0002

Data Index: 923284 (C4 (Web Text))

Max Activating Token Index: 106

Text #9

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0780. Min Act: -0.0002

Data Index: 40683 (C4 (Web Text))

Max Activating Token Index: 575

Text #10

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0725. Min Act: -0.0002

Data Index: 728179 (C4 (Web Text))

Max Activating Token Index: 1001

Text #11

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0783. Min Act: -0.0002

Data Index: 1214655 (C4 (Web Text))

Max Activating Token Index: 108

Text #12

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0752. Min Act: -0.0002

Data Index: 1184362 (C4 (Web Text))

Max Activating Token Index: 414

Text #13

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0746. Min Act: -0.0002

Data Index: 1203842 (C4 (Web Text))

Max Activating Token Index: 523

Text #14

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0735. Min Act: -0.0002

Data Index: 1290924 (C4 (Web Text))

Max Activating Token Index: 453

Text #15

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0757. Min Act: -0.0002

Data Index: 235634 (C4 (Web Text))

Max Activating Token Index: 320

Text #16

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0731. Min Act: -0.0002

Data Index: 533390 (C4 (Web Text))

Max Activating Token Index: 946

Text #17

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0725. Min Act: -0.0002

Data Index: 19345 (C4 (Web Text))

Max Activating Token Index: 753

Text #18

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0695. Min Act: -0.0002

Data Index: 1350950 (C4 (Web Text))

Max Activating Token Index: 242

Text #19

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0718. Min Act: -0.0002

Data Index: 1239318 (C4 (Web Text))

Max Activating Token Index: 583