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

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

Neuron 4437 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1718. Min Range: -2.1718

Max Act: 2.1718. Min Act: -0.0000

Data Index: 480349 (C4 (Web Text))

Max Activating Token Index: 96

Text #1

Max Range: 2.1718. Min Range: -2.1718

Max Act: 2.1428. Min Act: -0.0000

Data Index: 285117 (C4 (Web Text))

Max Activating Token Index: 791

Text #2

Max Range: 2.1718. Min Range: -2.1718

Max Act: 1.8071. Min Act: -0.0000

Data Index: 115827 (C4 (Web Text))

Max Activating Token Index: 678

Text #3

Max Range: 2.1718. Min Range: -2.1718

Max Act: 1.7497. Min Act: -0.0000

Data Index: 748161 (C4 (Web Text))

Max Activating Token Index: 732

Text #4

Max Range: 2.1718. Min Range: -2.1718

Max Act: 1.5603. Min Act: -0.0000

Data Index: 835302 (C4 (Web Text))

Max Activating Token Index: 971

Text #5

Max Range: 2.1718. Min Range: -2.1718

Max Act: 1.5485. Min Act: -0.0000

Data Index: 165716 (C4 (Web Text))

Max Activating Token Index: 517

Text #6

Max Range: 2.1718. Min Range: -2.1718

Max Act: 1.6632. Min Act: -0.0000

Data Index: 1187768 (C4 (Web Text))

Max Activating Token Index: 475

Text #7

Max Range: 2.1718. Min Range: -2.1718

Max Act: 1.5713. Min Act: -0.0000

Data Index: 8782 (C4 (Web Text))

Max Activating Token Index: 160

Text #8

Max Range: 2.1718. Min Range: -2.1718

Max Act: 1.6000. Min Act: -0.0000

Data Index: 1235696 (C4 (Web Text))

Max Activating Token Index: 682

Text #9

Max Range: 2.1718. Min Range: -2.1718

Max Act: 1.3708. Min Act: -0.0000

Data Index: 324187 (C4 (Web Text))

Max Activating Token Index: 869

Text #10

Max Range: 2.1718. Min Range: -2.1718

Max Act: 1.3712. Min Act: -0.0000

Data Index: 1181596 (C4 (Web Text))

Max Activating Token Index: 107

Text #11

Max Range: 2.1718. Min Range: -2.1718

Max Act: 1.3143. Min Act: -0.0000

Data Index: 77755 (C4 (Web Text))

Max Activating Token Index: 928

Text #12

Max Range: 2.1718. Min Range: -2.1718

Max Act: 1.3809. Min Act: -0.0000

Data Index: 1180614 (C4 (Web Text))

Max Activating Token Index: 857

Text #13

Max Range: 2.1718. Min Range: -2.1718

Max Act: 1.3720. Min Act: -0.0000

Data Index: 675458 (C4 (Web Text))

Max Activating Token Index: 767

Text #14

Max Range: 2.1718. Min Range: -2.1718

Max Act: 1.3437. Min Act: -0.0000

Data Index: 619142 (C4 (Web Text))

Max Activating Token Index: 641

Text #15

Max Range: 2.1718. Min Range: -2.1718

Max Act: 1.2462. Min Act: -0.0000

Data Index: 1047771 (C4 (Web Text))

Max Activating Token Index: 785

Text #16

Max Range: 2.1718. Min Range: -2.1718

Max Act: 1.2243. Min Act: -0.0000

Data Index: 1258753 (C4 (Web Text))

Max Activating Token Index: 628

Text #17

Max Range: 2.1718. Min Range: -2.1718

Max Act: 1.1977. Min Act: -0.0000

Data Index: 1146779 (C4 (Web Text))

Max Activating Token Index: 499

Text #18

Max Range: 2.1718. Min Range: -2.1718

Max Act: 1.1869. Min Act: -0.0000

Data Index: 622803 (C4 (Web Text))

Max Activating Token Index: 655

Text #19

Max Range: 2.1718. Min Range: -2.1718

Max Act: 1.1615. Min Act: -0.0000

Data Index: 601571 (C4 (Web Text))

Max Activating Token Index: 737