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

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

Neuron 1528 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8614. Min Range: -0.8614

Max Act: 0.8614. Min Act: -0.0002

Data Index: 962918 (C4 (Web Text))

Max Activating Token Index: 707

Text #1

Max Range: 0.8614. Min Range: -0.8614

Max Act: 0.8088. Min Act: -0.0002

Data Index: 968154 (C4 (Web Text))

Max Activating Token Index: 245

Text #2

Max Range: 0.8614. Min Range: -0.8614

Max Act: 0.8612. Min Act: -0.0002

Data Index: 1160743 (C4 (Web Text))

Max Activating Token Index: 808

Text #3

Max Range: 0.8614. Min Range: -0.8614

Max Act: 0.7820. Min Act: -0.0002

Data Index: 111069 (C4 (Web Text))

Max Activating Token Index: 459

Text #4

Max Range: 0.8614. Min Range: -0.8614

Max Act: 0.6480. Min Act: -0.0002

Data Index: 681867 (C4 (Web Text))

Max Activating Token Index: 311

Text #5

Max Range: 0.8614. Min Range: -0.8614

Max Act: 0.7562. Min Act: -0.0002

Data Index: 1113473 (C4 (Web Text))

Max Activating Token Index: 465

Text #6

Max Range: 0.8614. Min Range: -0.8614

Max Act: 0.7794. Min Act: -0.0002

Data Index: 775420 (C4 (Web Text))

Max Activating Token Index: 895

Text #7

Max Range: 0.8614. Min Range: -0.8614

Max Act: 0.8141. Min Act: -0.0002

Data Index: 642883 (C4 (Web Text))

Max Activating Token Index: 263

Text #8

Max Range: 0.8614. Min Range: -0.8614

Max Act: 0.6736. Min Act: -0.0002

Data Index: 885359 (C4 (Web Text))

Max Activating Token Index: 763

Text #9

Max Range: 0.8614. Min Range: -0.8614

Max Act: 0.7652. Min Act: -0.0002

Data Index: 692761 (C4 (Web Text))

Max Activating Token Index: 345

Text #10

Max Range: 0.8614. Min Range: -0.8614

Max Act: 0.4800. Min Act: -0.0002

Data Index: 933237 (C4 (Web Text))

Max Activating Token Index: 844

Text #11

Max Range: 0.8614. Min Range: -0.8614

Max Act: 0.6727. Min Act: -0.0002

Data Index: 704787 (C4 (Web Text))

Max Activating Token Index: 444

Text #12

Max Range: 0.8614. Min Range: -0.8614

Max Act: 0.5832. Min Act: -0.0002

Data Index: 187313 (C4 (Web Text))

Max Activating Token Index: 263

Text #13

Max Range: 0.8614. Min Range: -0.8614

Max Act: 0.6625. Min Act: -0.0002

Data Index: 987715 (C4 (Web Text))

Max Activating Token Index: 930

Text #14

Max Range: 0.8614. Min Range: -0.8614

Max Act: 0.6497. Min Act: -0.0002

Data Index: 116261 (C4 (Web Text))

Max Activating Token Index: 487

Text #15

Max Range: 0.8614. Min Range: -0.8614

Max Act: 0.6879. Min Act: -0.0002

Data Index: 277285 (C4 (Web Text))

Max Activating Token Index: 496

Text #16

Max Range: 0.8614. Min Range: -0.8614

Max Act: 0.5185. Min Act: -0.0002

Data Index: 1268867 (C4 (Web Text))

Max Activating Token Index: 195

Text #17

Max Range: 0.8614. Min Range: -0.8614

Max Act: 0.5810. Min Act: -0.0002

Data Index: 1206338 (C4 (Web Text))

Max Activating Token Index: 25

Text #18

Max Range: 0.8614. Min Range: -0.8614

Max Act: 0.6081. Min Act: -0.0002

Data Index: 1544070 (Python Code)

Max Activating Token Index: 655

Text #19

Max Range: 0.8614. Min Range: -0.8614

Max Act: 0.6069. Min Act: -0.0002

Data Index: 545306 (C4 (Web Text))

Max Activating Token Index: 284