Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1281 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0865. Min Act: -0.0002

Data Index: 1153556 (C4 (Web Text))

Max Activating Token Index: 449

Text #1

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0796. Min Act: -0.0001

Data Index: 45636 (C4 (Web Text))

Max Activating Token Index: 112

Text #2

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0744. Min Act: -0.0002

Data Index: 1213741 (C4 (Web Text))

Max Activating Token Index: 801

Text #3

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0743. Min Act: -0.0002

Data Index: 647119 (C4 (Web Text))

Max Activating Token Index: 760

Text #4

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0746. Min Act: -0.0001

Data Index: 702902 (C4 (Web Text))

Max Activating Token Index: 119

Text #5

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0705. Min Act: -0.0002

Data Index: 337432 (C4 (Web Text))

Max Activating Token Index: 524

Text #6

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0700. Min Act: -0.0002

Data Index: 736809 (C4 (Web Text))

Max Activating Token Index: 137

Text #7

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0691. Min Act: -0.0002

Data Index: 1231733 (C4 (Web Text))

Max Activating Token Index: 253

Text #8

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0681. Min Act: -0.0002

Data Index: 1120935 (C4 (Web Text))

Max Activating Token Index: 776

Text #9

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0689. Min Act: -0.0002

Data Index: 343147 (C4 (Web Text))

Max Activating Token Index: 510

Text #10

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0674. Min Act: -0.0001

Data Index: 756868 (C4 (Web Text))

Max Activating Token Index: 464

Text #11

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0672. Min Act: -0.0001

Data Index: 1181622 (C4 (Web Text))

Max Activating Token Index: 556

Text #12

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0672. Min Act: -0.0002

Data Index: 818909 (C4 (Web Text))

Max Activating Token Index: 237

Text #13

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0660. Min Act: -0.0001

Data Index: 738937 (C4 (Web Text))

Max Activating Token Index: 511

Text #14

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0675. Min Act: -0.0002

Data Index: 1078226 (C4 (Web Text))

Max Activating Token Index: 918

Text #15

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0657. Min Act: -0.0001

Data Index: 229587 (C4 (Web Text))

Max Activating Token Index: 706

Text #16

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0638. Min Act: -0.0001

Data Index: 546912 (C4 (Web Text))

Max Activating Token Index: 505

Text #17

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0648. Min Act: -0.0002

Data Index: 276645 (C4 (Web Text))

Max Activating Token Index: 372

Text #18

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0626. Min Act: -0.0002

Data Index: 884519 (C4 (Web Text))

Max Activating Token Index: 399

Text #19

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0626. Min Act: -0.0000

Data Index: 1076177 (C4 (Web Text))

Max Activating Token Index: 429