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

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

Neuron 5680 in Layer 0

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: 0.0832. Min Range: -0.0832

Max Act: 0.0832. Min Act: -0.0001

Data Index: 1454142 (Python Code)

Max Activating Token Index: 219

Text #1

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0819. Min Act: -0.0001

Data Index: 1475565 (Python Code)

Max Activating Token Index: 377

Text #2

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0803. Min Act: -0.0001

Data Index: 269362 (C4 (Web Text))

Max Activating Token Index: 10

Text #3

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0805. Min Act: -0.0001

Data Index: 1555412 (Python Code)

Max Activating Token Index: 290

Text #4

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0811. Min Act: -0.0001

Data Index: 1497657 (Python Code)

Max Activating Token Index: 579

Text #5

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0813. Min Act: -0.0001

Data Index: 1618904 (Python Code)

Max Activating Token Index: 518

Text #6

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0793. Min Act: -0.0001

Data Index: 1551032 (Python Code)

Max Activating Token Index: 981

Text #7

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0782. Min Act: -0.0001

Data Index: 1519039 (Python Code)

Max Activating Token Index: 71

Text #8

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0790. Min Act: -0.0001

Data Index: 1521331 (Python Code)

Max Activating Token Index: 624

Text #9

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0780. Min Act: -0.0001

Data Index: 857335 (C4 (Web Text))

Max Activating Token Index: 153

Text #10

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0761. Min Act: -0.0001

Data Index: 1531414 (Python Code)

Max Activating Token Index: 19

Text #11

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0770. Min Act: -0.0001

Data Index: 1006197 (C4 (Web Text))

Max Activating Token Index: 724

Text #12

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0769. Min Act: -0.0001

Data Index: 1404249 (Python Code)

Max Activating Token Index: 289

Text #13

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0768. Min Act: -0.0001

Data Index: 769423 (C4 (Web Text))

Max Activating Token Index: 454

Text #14

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0734. Min Act: -0.0001

Data Index: 175723 (C4 (Web Text))

Max Activating Token Index: 475

Text #15

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0745. Min Act: -0.0001

Data Index: 1013033 (C4 (Web Text))

Max Activating Token Index: 909

Text #16

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0740. Min Act: -0.0001

Data Index: 1193588 (C4 (Web Text))

Max Activating Token Index: 119

Text #17

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0750. Min Act: -0.0001

Data Index: 1512753 (Python Code)

Max Activating Token Index: 64

Text #18

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0727. Min Act: -0.0001

Data Index: 82553 (C4 (Web Text))

Max Activating Token Index: 873

Text #19

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0737. Min Act: -0.0001

Data Index: 1398247 (Python Code)

Max Activating Token Index: 70