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

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

Neuron 5040 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0908. Min Act: -0.0001

Data Index: 947830 (C4 (Web Text))

Max Activating Token Index: 979

Text #1

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0836. Min Act: -0.0001

Data Index: 210834 (C4 (Web Text))

Max Activating Token Index: 175

Text #2

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0730. Min Act: -0.0001

Data Index: 321844 (C4 (Web Text))

Max Activating Token Index: 743

Text #3

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0684. Min Act: -0.0000

Data Index: 1028817 (C4 (Web Text))

Max Activating Token Index: 138

Text #4

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0729. Min Act: -0.0001

Data Index: 1161440 (C4 (Web Text))

Max Activating Token Index: 254

Text #5

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0737. Min Act: -0.0001

Data Index: 370581 (C4 (Web Text))

Max Activating Token Index: 252

Text #6

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0640. Min Act: -0.0001

Data Index: 875881 (C4 (Web Text))

Max Activating Token Index: 813

Text #7

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0709. Min Act: -0.0000

Data Index: 425946 (C4 (Web Text))

Max Activating Token Index: 89

Text #8

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0763. Min Act: -0.0001

Data Index: 965914 (C4 (Web Text))

Max Activating Token Index: 98

Text #9

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0718. Min Act: -0.0001

Data Index: 91832 (C4 (Web Text))

Max Activating Token Index: 21

Text #10

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0730. Min Act: -0.0000

Data Index: 1135305 (C4 (Web Text))

Max Activating Token Index: 931

Text #11

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0674. Min Act: -0.0001

Data Index: 1045164 (C4 (Web Text))

Max Activating Token Index: 358

Text #12

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0686. Min Act: -0.0001

Data Index: 402054 (C4 (Web Text))

Max Activating Token Index: 503

Text #13

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0692. Min Act: -0.0001

Data Index: 353958 (C4 (Web Text))

Max Activating Token Index: 708

Text #14

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0644. Min Act: -0.0001

Data Index: 913621 (C4 (Web Text))

Max Activating Token Index: 663

Text #15

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0663. Min Act: -0.0000

Data Index: 265697 (C4 (Web Text))

Max Activating Token Index: 277

Text #16

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0696. Min Act: -0.0001

Data Index: 540901 (C4 (Web Text))

Max Activating Token Index: 569

Text #17

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0650. Min Act: -0.0000

Data Index: 80384 (C4 (Web Text))

Max Activating Token Index: 950

Text #18

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0705. Min Act: -0.0001

Data Index: 962532 (C4 (Web Text))

Max Activating Token Index: 447

Text #19

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0642. Min Act: -0.0001

Data Index: 193597 (C4 (Web Text))

Max Activating Token Index: 837