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

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

Neuron 4409 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0984. Min Range: -0.0984

Max Act: 0.0984. Min Act: -0.0001

Data Index: 811599 (C4 (Web Text))

Max Activating Token Index: 865

Text #1

Max Range: 0.0984. Min Range: -0.0984

Max Act: 0.0748. Min Act: -0.0001

Data Index: 417520 (C4 (Web Text))

Max Activating Token Index: 224

Text #2

Max Range: 0.0984. Min Range: -0.0984

Max Act: 0.0801. Min Act: -0.0001

Data Index: 114298 (C4 (Web Text))

Max Activating Token Index: 624

Text #3

Max Range: 0.0984. Min Range: -0.0984

Max Act: 0.0825. Min Act: -0.0001

Data Index: 108071 (C4 (Web Text))

Max Activating Token Index: 627

Text #4

Max Range: 0.0984. Min Range: -0.0984

Max Act: 0.0739. Min Act: -0.0001

Data Index: 1016872 (C4 (Web Text))

Max Activating Token Index: 262

Text #5

Max Range: 0.0984. Min Range: -0.0984

Max Act: 0.0688. Min Act: -0.0001

Data Index: 1267920 (C4 (Web Text))

Max Activating Token Index: 640

Text #6

Max Range: 0.0984. Min Range: -0.0984

Max Act: 0.0726. Min Act: -0.0001

Data Index: 288235 (C4 (Web Text))

Max Activating Token Index: 516

Text #7

Max Range: 0.0984. Min Range: -0.0984

Max Act: 0.0721. Min Act: -0.0001

Data Index: 1050854 (C4 (Web Text))

Max Activating Token Index: 89

Text #8

Max Range: 0.0984. Min Range: -0.0984

Max Act: 0.0723. Min Act: -0.0001

Data Index: 954671 (C4 (Web Text))

Max Activating Token Index: 642

Text #9

Max Range: 0.0984. Min Range: -0.0984

Max Act: 0.0701. Min Act: -0.0001

Data Index: 1215951 (C4 (Web Text))

Max Activating Token Index: 26

Text #10

Max Range: 0.0984. Min Range: -0.0984

Max Act: 0.0654. Min Act: -0.0001

Data Index: 700737 (C4 (Web Text))

Max Activating Token Index: 1000

Text #11

Max Range: 0.0984. Min Range: -0.0984

Max Act: 0.0744. Min Act: -0.0000

Data Index: 739035 (C4 (Web Text))

Max Activating Token Index: 998

Text #12

Max Range: 0.0984. Min Range: -0.0984

Max Act: 0.0681. Min Act: -0.0000

Data Index: 1218485 (C4 (Web Text))

Max Activating Token Index: 778

Text #13

Max Range: 0.0984. Min Range: -0.0984

Max Act: 0.0681. Min Act: -0.0001

Data Index: 520424 (C4 (Web Text))

Max Activating Token Index: 451

Text #14

Max Range: 0.0984. Min Range: -0.0984

Max Act: 0.0660. Min Act: -0.0001

Data Index: 859717 (C4 (Web Text))

Max Activating Token Index: 335

Text #15

Max Range: 0.0984. Min Range: -0.0984

Max Act: 0.0647. Min Act: -0.0001

Data Index: 354472 (C4 (Web Text))

Max Activating Token Index: 356

Text #16

Max Range: 0.0984. Min Range: -0.0984

Max Act: 0.0713. Min Act: -0.0001

Data Index: 786963 (C4 (Web Text))

Max Activating Token Index: 579

Text #17

Max Range: 0.0984. Min Range: -0.0984

Max Act: 0.0661. Min Act: -0.0001

Data Index: 566086 (C4 (Web Text))

Max Activating Token Index: 262

Text #18

Max Range: 0.0984. Min Range: -0.0984

Max Act: 0.0654. Min Act: -0.0001

Data Index: 54452 (C4 (Web Text))

Max Activating Token Index: 323

Text #19

Max Range: 0.0984. Min Range: -0.0984

Max Act: 0.0641. Min Act: -0.0001

Data Index: 475133 (C4 (Web Text))

Max Activating Token Index: 852