Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2778 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0889. Min Act: -0.0001

Data Index: 376909 (C4 (Web Text))

Max Activating Token Index: 606

Text #1

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0730. Min Act: -0.0001

Data Index: 1067247 (C4 (Web Text))

Max Activating Token Index: 584

Text #2

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0680. Min Act: -0.0002

Data Index: 874015 (C4 (Web Text))

Max Activating Token Index: 810

Text #3

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0762. Min Act: -0.0001

Data Index: 444216 (C4 (Web Text))

Max Activating Token Index: 792

Text #4

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0739. Min Act: -0.0001

Data Index: 610542 (C4 (Web Text))

Max Activating Token Index: 808

Text #5

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0761. Min Act: -0.0001

Data Index: 632868 (C4 (Web Text))

Max Activating Token Index: 538

Text #6

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0640. Min Act: -0.0001

Data Index: 400809 (C4 (Web Text))

Max Activating Token Index: 748

Text #7

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0715. Min Act: -0.0001

Data Index: 1086250 (C4 (Web Text))

Max Activating Token Index: 152

Text #8

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0609. Min Act: -0.0001

Data Index: 1051759 (C4 (Web Text))

Max Activating Token Index: 297

Text #9

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0686. Min Act: -0.0001

Data Index: 647132 (C4 (Web Text))

Max Activating Token Index: 742

Text #10

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0681. Min Act: -0.0001

Data Index: 34882 (C4 (Web Text))

Max Activating Token Index: 700

Text #11

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0638. Min Act: -0.0001

Data Index: 352562 (C4 (Web Text))

Max Activating Token Index: 59

Text #12

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0633. Min Act: -0.0001

Data Index: 1461068 (Python Code)

Max Activating Token Index: 902

Text #13

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0607. Min Act: -0.0001

Data Index: 159111 (C4 (Web Text))

Max Activating Token Index: 345

Text #14

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0621. Min Act: -0.0001

Data Index: 1423593 (Python Code)

Max Activating Token Index: 82

Text #15

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0638. Min Act: -0.0001

Data Index: 188711 (C4 (Web Text))

Max Activating Token Index: 72

Text #16

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0597. Min Act: -0.0001

Data Index: 753444 (C4 (Web Text))

Max Activating Token Index: 622

Text #17

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0612. Min Act: -0.0001

Data Index: 1258801 (C4 (Web Text))

Max Activating Token Index: 849

Text #18

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0600. Min Act: -0.0001

Data Index: 343439 (C4 (Web Text))

Max Activating Token Index: 885

Text #19

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0530. Min Act: -0.0001

Data Index: 1579373 (Python Code)

Max Activating Token Index: 244