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

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

Neuron 1560 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0836. Min Act: -0.0002

Data Index: 800055 (C4 (Web Text))

Max Activating Token Index: 324

Text #1

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0829. Min Act: -0.0002

Data Index: 425214 (C4 (Web Text))

Max Activating Token Index: 4

Text #2

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0843. Min Act: -0.0002

Data Index: 231744 (C4 (Web Text))

Max Activating Token Index: 919

Text #3

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0813. Min Act: -0.0002

Data Index: 1302213 (C4 (Web Text))

Max Activating Token Index: 824

Text #4

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0811. Min Act: -0.0002

Data Index: 386648 (C4 (Web Text))

Max Activating Token Index: 789

Text #5

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0809. Min Act: -0.0002

Data Index: 274161 (C4 (Web Text))

Max Activating Token Index: 838

Text #6

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0786. Min Act: -0.0002

Data Index: 1499234 (Python Code)

Max Activating Token Index: 2

Text #7

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0786. Min Act: -0.0002

Data Index: 794817 (C4 (Web Text))

Max Activating Token Index: 2

Text #8

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0786. Min Act: -0.0002

Data Index: 1169292 (C4 (Web Text))

Max Activating Token Index: 2

Text #9

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0812. Min Act: -0.0002

Data Index: 1320214 (C4 (Web Text))

Max Activating Token Index: 147

Text #10

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0806. Min Act: -0.0002

Data Index: 903902 (C4 (Web Text))

Max Activating Token Index: 600

Text #11

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0787. Min Act: -0.0002

Data Index: 13797 (C4 (Web Text))

Max Activating Token Index: 818

Text #12

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0790. Min Act: -0.0002

Data Index: 157573 (C4 (Web Text))

Max Activating Token Index: 972

Text #13

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0795. Min Act: -0.0002

Data Index: 753733 (C4 (Web Text))

Max Activating Token Index: 727

Text #14

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0789. Min Act: -0.0002

Data Index: 343693 (C4 (Web Text))

Max Activating Token Index: 743

Text #15

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0787. Min Act: -0.0002

Data Index: 397106 (C4 (Web Text))

Max Activating Token Index: 783

Text #16

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0787. Min Act: -0.0002

Data Index: 1328362 (C4 (Web Text))

Max Activating Token Index: 595

Text #17

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0789. Min Act: -0.0002

Data Index: 1185121 (C4 (Web Text))

Max Activating Token Index: 589

Text #18

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0761. Min Act: -0.0002

Data Index: 1313967 (C4 (Web Text))

Max Activating Token Index: 689

Text #19

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0777. Min Act: -0.0002

Data Index: 945870 (C4 (Web Text))

Max Activating Token Index: 334