Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3298 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0971. Min Range: -0.0971

Max Act: 0.0971. Min Act: -0.0002

Data Index: 542792 (C4 (Web Text))

Max Activating Token Index: 8

Text #1

Max Range: 0.0971. Min Range: -0.0971

Max Act: 0.0887. Min Act: -0.0002

Data Index: 678590 (C4 (Web Text))

Max Activating Token Index: 44

Text #2

Max Range: 0.0971. Min Range: -0.0971

Max Act: 0.0810. Min Act: -0.0002

Data Index: 69096 (C4 (Web Text))

Max Activating Token Index: 13

Text #3

Max Range: 0.0971. Min Range: -0.0971

Max Act: 0.0824. Min Act: -0.0002

Data Index: 333084 (C4 (Web Text))

Max Activating Token Index: 520

Text #4

Max Range: 0.0971. Min Range: -0.0971

Max Act: 0.0771. Min Act: -0.0002

Data Index: 299937 (C4 (Web Text))

Max Activating Token Index: 20

Text #5

Max Range: 0.0971. Min Range: -0.0971

Max Act: 0.0757. Min Act: -0.0002

Data Index: 1055654 (C4 (Web Text))

Max Activating Token Index: 1006

Text #6

Max Range: 0.0971. Min Range: -0.0971

Max Act: 0.0751. Min Act: -0.0002

Data Index: 203605 (C4 (Web Text))

Max Activating Token Index: 599

Text #7

Max Range: 0.0971. Min Range: -0.0971

Max Act: 0.0755. Min Act: -0.0002

Data Index: 910393 (C4 (Web Text))

Max Activating Token Index: 12

Text #8

Max Range: 0.0971. Min Range: -0.0971

Max Act: 0.0735. Min Act: -0.0002

Data Index: 1039681 (C4 (Web Text))

Max Activating Token Index: 274

Text #9

Max Range: 0.0971. Min Range: -0.0971

Max Act: 0.0660. Min Act: -0.0002

Data Index: 1216264 (C4 (Web Text))

Max Activating Token Index: 882

Text #10

Max Range: 0.0971. Min Range: -0.0971

Max Act: 0.0734. Min Act: -0.0002

Data Index: 675047 (C4 (Web Text))

Max Activating Token Index: 40

Text #11

Max Range: 0.0971. Min Range: -0.0971

Max Act: 0.0712. Min Act: -0.0002

Data Index: 32965 (C4 (Web Text))

Max Activating Token Index: 437

Text #12

Max Range: 0.0971. Min Range: -0.0971

Max Act: 0.0676. Min Act: -0.0002

Data Index: 1071391 (C4 (Web Text))

Max Activating Token Index: 905

Text #13

Max Range: 0.0971. Min Range: -0.0971

Max Act: 0.0722. Min Act: -0.0002

Data Index: 461369 (C4 (Web Text))

Max Activating Token Index: 990

Text #14

Max Range: 0.0971. Min Range: -0.0971

Max Act: 0.0775. Min Act: -0.0002

Data Index: 1214971 (C4 (Web Text))

Max Activating Token Index: 656

Text #15

Max Range: 0.0971. Min Range: -0.0971

Max Act: 0.0721. Min Act: -0.0002

Data Index: 1187831 (C4 (Web Text))

Max Activating Token Index: 622

Text #16

Max Range: 0.0971. Min Range: -0.0971

Max Act: 0.0717. Min Act: -0.0002

Data Index: 500037 (C4 (Web Text))

Max Activating Token Index: 40

Text #17

Max Range: 0.0971. Min Range: -0.0971

Max Act: 0.0664. Min Act: -0.0002

Data Index: 1083110 (C4 (Web Text))

Max Activating Token Index: 67

Text #18

Max Range: 0.0971. Min Range: -0.0971

Max Act: 0.0738. Min Act: -0.0002

Data Index: 909292 (C4 (Web Text))

Max Activating Token Index: 919

Text #19

Max Range: 0.0971. Min Range: -0.0971

Max Act: 0.0686. Min Act: -0.0002

Data Index: 6075 (C4 (Web Text))

Max Activating Token Index: 917