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

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

Neuron 4600 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.1717. Min Range: -2.1717

Max Act: 2.1717. Min Act: -0.0000

Data Index: 781186 (C4 (Web Text))

Max Activating Token Index: 848

Text #1

Max Range: 2.1717. Min Range: -2.1717

Max Act: 2.0731. Min Act: -0.0000

Data Index: 1197830 (C4 (Web Text))

Max Activating Token Index: 922

Text #2

Max Range: 2.1717. Min Range: -2.1717

Max Act: 2.0859. Min Act: -0.0000

Data Index: 714783 (C4 (Web Text))

Max Activating Token Index: 394

Text #3

Max Range: 2.1717. Min Range: -2.1717

Max Act: 1.9315. Min Act: -0.0000

Data Index: 44509 (C4 (Web Text))

Max Activating Token Index: 688

Text #4

Max Range: 2.1717. Min Range: -2.1717

Max Act: 1.9642. Min Act: -0.0000

Data Index: 694629 (C4 (Web Text))

Max Activating Token Index: 493

Text #5

Max Range: 2.1717. Min Range: -2.1717

Max Act: 1.8245. Min Act: -0.0000

Data Index: 153043 (C4 (Web Text))

Max Activating Token Index: 134

Text #6

Max Range: 2.1717. Min Range: -2.1717

Max Act: 1.7956. Min Act: -0.0000

Data Index: 763126 (C4 (Web Text))

Max Activating Token Index: 522

Text #7

Max Range: 2.1717. Min Range: -2.1717

Max Act: 1.8794. Min Act: -0.0000

Data Index: 702231 (C4 (Web Text))

Max Activating Token Index: 725

Text #8

Max Range: 2.1717. Min Range: -2.1717

Max Act: 1.8548. Min Act: -0.0000

Data Index: 441837 (C4 (Web Text))

Max Activating Token Index: 977

Text #9

Max Range: 2.1717. Min Range: -2.1717

Max Act: 1.7769. Min Act: -0.0000

Data Index: 422622 (C4 (Web Text))

Max Activating Token Index: 516

Text #10

Max Range: 2.1717. Min Range: -2.1717

Max Act: 1.8010. Min Act: -0.0000

Data Index: 129640 (C4 (Web Text))

Max Activating Token Index: 467

Text #11

Max Range: 2.1717. Min Range: -2.1717

Max Act: 1.8267. Min Act: -0.0000

Data Index: 685111 (C4 (Web Text))

Max Activating Token Index: 481

Text #12

Max Range: 2.1717. Min Range: -2.1717

Max Act: 1.6044. Min Act: -0.0000

Data Index: 904210 (C4 (Web Text))

Max Activating Token Index: 514

Text #13

Max Range: 2.1717. Min Range: -2.1717

Max Act: 1.7788. Min Act: -0.0000

Data Index: 521801 (C4 (Web Text))

Max Activating Token Index: 926

Text #14

Max Range: 2.1717. Min Range: -2.1717

Max Act: 1.7990. Min Act: -0.0000

Data Index: 1505 (C4 (Web Text))

Max Activating Token Index: 419

Text #15

Max Range: 2.1717. Min Range: -2.1717

Max Act: 1.5418. Min Act: -0.0000

Data Index: 262917 (C4 (Web Text))

Max Activating Token Index: 385

Text #16

Max Range: 2.1717. Min Range: -2.1717

Max Act: 1.4758. Min Act: -0.0000

Data Index: 85340 (C4 (Web Text))

Max Activating Token Index: 765

Text #17

Max Range: 2.1717. Min Range: -2.1717

Max Act: 1.4895. Min Act: -0.0000

Data Index: 373235 (C4 (Web Text))

Max Activating Token Index: 158

Text #18

Max Range: 2.1717. Min Range: -2.1717

Max Act: 1.5749. Min Act: -0.0000

Data Index: 836837 (C4 (Web Text))

Max Activating Token Index: 656

Text #19

Max Range: 2.1717. Min Range: -2.1717

Max Act: 1.4980. Min Act: -0.0000

Data Index: 1074455 (C4 (Web Text))

Max Activating Token Index: 283