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

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

Neuron 5739 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: 0.0803. Min Range: -0.0803

Max Act: 0.0803. Min Act: -0.0001

Data Index: 936134 (C4 (Web Text))

Max Activating Token Index: 2

Text #1

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0803. Min Act: -0.0001

Data Index: 24869 (C4 (Web Text))

Max Activating Token Index: 2

Text #2

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0779. Min Act: -0.0001

Data Index: 236697 (C4 (Web Text))

Max Activating Token Index: 45

Text #3

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0776. Min Act: -0.0001

Data Index: 209214 (C4 (Web Text))

Max Activating Token Index: 32

Text #4

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0746. Min Act: -0.0001

Data Index: 1125991 (C4 (Web Text))

Max Activating Token Index: 192

Text #5

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0750. Min Act: -0.0001

Data Index: 893366 (C4 (Web Text))

Max Activating Token Index: 501

Text #6

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0742. Min Act: -0.0001

Data Index: 1355945 (C4 (Web Text))

Max Activating Token Index: 937

Text #7

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0746. Min Act: -0.0001

Data Index: 568482 (C4 (Web Text))

Max Activating Token Index: 50

Text #8

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0745. Min Act: -0.0001

Data Index: 1528908 (Python Code)

Max Activating Token Index: 262

Text #9

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0737. Min Act: -0.0001

Data Index: 675926 (C4 (Web Text))

Max Activating Token Index: 73

Text #10

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0750. Min Act: -0.0001

Data Index: 839602 (C4 (Web Text))

Max Activating Token Index: 838

Text #11

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0734. Min Act: -0.0001

Data Index: 1274480 (C4 (Web Text))

Max Activating Token Index: 923

Text #12

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0735. Min Act: -0.0001

Data Index: 92618 (C4 (Web Text))

Max Activating Token Index: 793

Text #13

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0731. Min Act: -0.0001

Data Index: 1186460 (C4 (Web Text))

Max Activating Token Index: 350

Text #14

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0730. Min Act: -0.0001

Data Index: 1311760 (C4 (Web Text))

Max Activating Token Index: 40

Text #15

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0722. Min Act: -0.0001

Data Index: 477205 (C4 (Web Text))

Max Activating Token Index: 170

Text #16

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0727. Min Act: -0.0001

Data Index: 790771 (C4 (Web Text))

Max Activating Token Index: 1001

Text #17

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0718. Min Act: -0.0001

Data Index: 1354753 (C4 (Web Text))

Max Activating Token Index: 910

Text #18

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0716. Min Act: -0.0001

Data Index: 1440814 (Python Code)

Max Activating Token Index: 432

Text #19

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0720. Min Act: -0.0001

Data Index: 583802 (C4 (Web Text))

Max Activating Token Index: 37