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

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

Neuron 2439 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1362. Min Range: -0.1362

Max Act: 0.1362. Min Act: -0.0000

Data Index: 984624 (C4 (Web Text))

Max Activating Token Index: 969

Text #1

Max Range: 0.1362. Min Range: -0.1362

Max Act: 0.0936. Min Act: -0.0000

Data Index: 696558 (C4 (Web Text))

Max Activating Token Index: 866

Text #2

Max Range: 0.1362. Min Range: -0.1362

Max Act: 0.0996. Min Act: -0.0000

Data Index: 749467 (C4 (Web Text))

Max Activating Token Index: 206

Text #3

Max Range: 0.1362. Min Range: -0.1362

Max Act: 0.0917. Min Act: -0.0000

Data Index: 238245 (C4 (Web Text))

Max Activating Token Index: 825

Text #4

Max Range: 0.1362. Min Range: -0.1362

Max Act: 0.0888. Min Act: -0.0001

Data Index: 680602 (C4 (Web Text))

Max Activating Token Index: 655

Text #5

Max Range: 0.1362. Min Range: -0.1362

Max Act: 0.0891. Min Act: -0.0000

Data Index: 1356066 (C4 (Web Text))

Max Activating Token Index: 102

Text #6

Max Range: 0.1362. Min Range: -0.1362

Max Act: 0.0788. Min Act: -0.0000

Data Index: 179028 (C4 (Web Text))

Max Activating Token Index: 240

Text #7

Max Range: 0.1362. Min Range: -0.1362

Max Act: 0.0803. Min Act: -0.0000

Data Index: 1121185 (C4 (Web Text))

Max Activating Token Index: 800

Text #8

Max Range: 0.1362. Min Range: -0.1362

Max Act: 0.0858. Min Act: -0.0000

Data Index: 1264682 (C4 (Web Text))

Max Activating Token Index: 979

Text #9

Max Range: 0.1362. Min Range: -0.1362

Max Act: 0.0815. Min Act: -0.0000

Data Index: 617614 (C4 (Web Text))

Max Activating Token Index: 711

Text #10

Max Range: 0.1362. Min Range: -0.1362

Max Act: 0.0749. Min Act: -0.0000

Data Index: 218666 (C4 (Web Text))

Max Activating Token Index: 713

Text #11

Max Range: 0.1362. Min Range: -0.1362

Max Act: 0.0801. Min Act: -0.0000

Data Index: 56837 (C4 (Web Text))

Max Activating Token Index: 799

Text #12

Max Range: 0.1362. Min Range: -0.1362

Max Act: 0.0829. Min Act: -0.0000

Data Index: 581676 (C4 (Web Text))

Max Activating Token Index: 766

Text #13

Max Range: 0.1362. Min Range: -0.1362

Max Act: 0.0758. Min Act: -0.0000

Data Index: 887786 (C4 (Web Text))

Max Activating Token Index: 459

Text #14

Max Range: 0.1362. Min Range: -0.1362

Max Act: 0.0762. Min Act: -0.0000

Data Index: 820876 (C4 (Web Text))

Max Activating Token Index: 1015

Text #15

Max Range: 0.1362. Min Range: -0.1362

Max Act: 0.0736. Min Act: -0.0000

Data Index: 1118939 (C4 (Web Text))

Max Activating Token Index: 259

Text #16

Max Range: 0.1362. Min Range: -0.1362

Max Act: 0.0741. Min Act: -0.0000

Data Index: 717047 (C4 (Web Text))

Max Activating Token Index: 853

Text #17

Max Range: 0.1362. Min Range: -0.1362

Max Act: 0.0782. Min Act: -0.0000

Data Index: 1414609 (Python Code)

Max Activating Token Index: 855

Text #18

Max Range: 0.1362. Min Range: -0.1362

Max Act: 0.0758. Min Act: -0.0001

Data Index: 1355317 (C4 (Web Text))

Max Activating Token Index: 905

Text #19

Max Range: 0.1362. Min Range: -0.1362

Max Act: 0.0797. Min Act: -0.0001

Data Index: 1320351 (C4 (Web Text))

Max Activating Token Index: 722