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

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

Neuron 3729 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2684. Min Range: -1.2684

Max Act: 1.2684. Min Act: -0.0000

Data Index: 128442 (C4 (Web Text))

Max Activating Token Index: 961

Text #1

Max Range: 1.2684. Min Range: -1.2684

Max Act: 1.1454. Min Act: -0.0000

Data Index: 330589 (C4 (Web Text))

Max Activating Token Index: 406

Text #2

Max Range: 1.2684. Min Range: -1.2684

Max Act: 1.0973. Min Act: -0.0000

Data Index: 1130804 (C4 (Web Text))

Max Activating Token Index: 42

Text #3

Max Range: 1.2684. Min Range: -1.2684

Max Act: 1.0879. Min Act: -0.0000

Data Index: 963726 (C4 (Web Text))

Max Activating Token Index: 208

Text #4

Max Range: 1.2684. Min Range: -1.2684

Max Act: 1.0190. Min Act: -0.0000

Data Index: 1537526 (Python Code)

Max Activating Token Index: 639

Text #5

Max Range: 1.2684. Min Range: -1.2684

Max Act: 1.0224. Min Act: -0.0000

Data Index: 814780 (C4 (Web Text))

Max Activating Token Index: 591

Text #6

Max Range: 1.2684. Min Range: -1.2684

Max Act: 1.0553. Min Act: -0.0000

Data Index: 116721 (C4 (Web Text))

Max Activating Token Index: 397

Text #7

Max Range: 1.2684. Min Range: -1.2684

Max Act: 0.9455. Min Act: -0.0000

Data Index: 846203 (C4 (Web Text))

Max Activating Token Index: 873

Text #8

Max Range: 1.2684. Min Range: -1.2684

Max Act: 0.9457. Min Act: -0.0000

Data Index: 930716 (C4 (Web Text))

Max Activating Token Index: 63

Text #9

Max Range: 1.2684. Min Range: -1.2684

Max Act: 0.9403. Min Act: -0.0000

Data Index: 725996 (C4 (Web Text))

Max Activating Token Index: 958

Text #10

Max Range: 1.2684. Min Range: -1.2684

Max Act: 0.8811. Min Act: -0.0000

Data Index: 1198575 (C4 (Web Text))

Max Activating Token Index: 321

Text #11

Max Range: 1.2684. Min Range: -1.2684

Max Act: 1.0209. Min Act: -0.0000

Data Index: 257139 (C4 (Web Text))

Max Activating Token Index: 396

Text #12

Max Range: 1.2684. Min Range: -1.2684

Max Act: 0.9045. Min Act: -0.0000

Data Index: 1590941 (Python Code)

Max Activating Token Index: 498

Text #13

Max Range: 1.2684. Min Range: -1.2684

Max Act: 0.8523. Min Act: -0.0000

Data Index: 384777 (C4 (Web Text))

Max Activating Token Index: 295

Text #14

Max Range: 1.2684. Min Range: -1.2684

Max Act: 0.8873. Min Act: -0.0000

Data Index: 374925 (C4 (Web Text))

Max Activating Token Index: 79

Text #15

Max Range: 1.2684. Min Range: -1.2684

Max Act: 0.8441. Min Act: -0.0000

Data Index: 712672 (C4 (Web Text))

Max Activating Token Index: 636

Text #16

Max Range: 1.2684. Min Range: -1.2684

Max Act: 0.8846. Min Act: -0.0000

Data Index: 1003135 (C4 (Web Text))

Max Activating Token Index: 151

Text #17

Max Range: 1.2684. Min Range: -1.2684

Max Act: 0.8440. Min Act: -0.0000

Data Index: 67429 (C4 (Web Text))

Max Activating Token Index: 687

Text #18

Max Range: 1.2684. Min Range: -1.2684

Max Act: 0.8694. Min Act: -0.0000

Data Index: 106584 (C4 (Web Text))

Max Activating Token Index: 554

Text #19

Max Range: 1.2684. Min Range: -1.2684

Max Act: 0.8642. Min Act: -0.0000

Data Index: 872629 (C4 (Web Text))

Max Activating Token Index: 948