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

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

Neuron 5953 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5718. Min Range: -2.5718

Max Act: 2.5718. Min Act: -0.0000

Data Index: 1485197 (Python Code)

Max Activating Token Index: 48

Text #1

Max Range: 2.5718. Min Range: -2.5718

Max Act: 2.4814. Min Act: -0.0000

Data Index: 467072 (C4 (Web Text))

Max Activating Token Index: 839

Text #2

Max Range: 2.5718. Min Range: -2.5718

Max Act: 2.0988. Min Act: -0.0000

Data Index: 1257698 (C4 (Web Text))

Max Activating Token Index: 353

Text #3

Max Range: 2.5718. Min Range: -2.5718

Max Act: 2.4447. Min Act: -0.0000

Data Index: 1526564 (Python Code)

Max Activating Token Index: 239

Text #4

Max Range: 2.5718. Min Range: -2.5718

Max Act: 2.2406. Min Act: -0.0000

Data Index: 1045868 (C4 (Web Text))

Max Activating Token Index: 221

Text #5

Max Range: 2.5718. Min Range: -2.5718

Max Act: 2.4746. Min Act: -0.0000

Data Index: 1478936 (Python Code)

Max Activating Token Index: 980

Text #6

Max Range: 2.5718. Min Range: -2.5718

Max Act: 2.2831. Min Act: -0.0000

Data Index: 346891 (C4 (Web Text))

Max Activating Token Index: 522

Text #7

Max Range: 2.5718. Min Range: -2.5718

Max Act: 2.2866. Min Act: -0.0000

Data Index: 1574500 (Python Code)

Max Activating Token Index: 138

Text #8

Max Range: 2.5718. Min Range: -2.5718

Max Act: 2.2035. Min Act: -0.0000

Data Index: 1616846 (Python Code)

Max Activating Token Index: 205

Text #9

Max Range: 2.5718. Min Range: -2.5718

Max Act: 2.2106. Min Act: -0.0000

Data Index: 602416 (C4 (Web Text))

Max Activating Token Index: 144

Text #10

Max Range: 2.5718. Min Range: -2.5718

Max Act: 2.1707. Min Act: -0.0000

Data Index: 1496495 (Python Code)

Max Activating Token Index: 174

Text #11

Max Range: 2.5718. Min Range: -2.5718

Max Act: 2.1634. Min Act: -0.0000

Data Index: 424734 (C4 (Web Text))

Max Activating Token Index: 830

Text #12

Max Range: 2.5718. Min Range: -2.5718

Max Act: 2.2785. Min Act: -0.0000

Data Index: 1434152 (Python Code)

Max Activating Token Index: 438

Text #13

Max Range: 2.5718. Min Range: -2.5718

Max Act: 2.0192. Min Act: -0.0000

Data Index: 664586 (C4 (Web Text))

Max Activating Token Index: 165

Text #14

Max Range: 2.5718. Min Range: -2.5718

Max Act: 2.0195. Min Act: -0.0000

Data Index: 1451794 (Python Code)

Max Activating Token Index: 640

Text #15

Max Range: 2.5718. Min Range: -2.5718

Max Act: 1.9838. Min Act: -0.0000

Data Index: 347829 (C4 (Web Text))

Max Activating Token Index: 385

Text #16

Max Range: 2.5718. Min Range: -2.5718

Max Act: 2.3360. Min Act: -0.0000

Data Index: 1612592 (Python Code)

Max Activating Token Index: 382

Text #17

Max Range: 2.5718. Min Range: -2.5718

Max Act: 2.2174. Min Act: -0.0000

Data Index: 393162 (C4 (Web Text))

Max Activating Token Index: 139

Text #18

Max Range: 2.5718. Min Range: -2.5718

Max Act: 2.2117. Min Act: -0.0000

Data Index: 1447000 (Python Code)

Max Activating Token Index: 114

Text #19

Max Range: 2.5718. Min Range: -2.5718

Max Act: 2.2018. Min Act: -0.0000

Data Index: 1392641 (Python Code)

Max Activating Token Index: 217