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

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

Neuron 872 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: 0.0797. Min Range: -0.0797

Max Act: 0.0795. Min Act: -0.0002

Data Index: 720689 (C4 (Web Text))

Max Activating Token Index: 286

Text #1

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0755. Min Act: -0.0002

Data Index: 730600 (C4 (Web Text))

Max Activating Token Index: 974

Text #2

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0786. Min Act: -0.0002

Data Index: 705133 (C4 (Web Text))

Max Activating Token Index: 823

Text #3

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0739. Min Act: -0.0002

Data Index: 1338226 (C4 (Web Text))

Max Activating Token Index: 556

Text #4

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0770. Min Act: -0.0001

Data Index: 542133 (C4 (Web Text))

Max Activating Token Index: 556

Text #5

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0797. Min Act: -0.0001

Data Index: 214886 (C4 (Web Text))

Max Activating Token Index: 872

Text #6

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0753. Min Act: -0.0002

Data Index: 133354 (C4 (Web Text))

Max Activating Token Index: 183

Text #7

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0746. Min Act: -0.0001

Data Index: 1057425 (C4 (Web Text))

Max Activating Token Index: 493

Text #8

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0741. Min Act: -0.0002

Data Index: 869409 (C4 (Web Text))

Max Activating Token Index: 255

Text #9

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0737. Min Act: -0.0002

Data Index: 18744 (C4 (Web Text))

Max Activating Token Index: 433

Text #10

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0728. Min Act: -0.0002

Data Index: 935043 (C4 (Web Text))

Max Activating Token Index: 940

Text #11

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0699. Min Act: -0.0002

Data Index: 888625 (C4 (Web Text))

Max Activating Token Index: 682

Text #12

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0715. Min Act: -0.0002

Data Index: 271267 (C4 (Web Text))

Max Activating Token Index: 428

Text #13

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0716. Min Act: -0.0002

Data Index: 809819 (C4 (Web Text))

Max Activating Token Index: 802

Text #14

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0766. Min Act: -0.0002

Data Index: 949963 (C4 (Web Text))

Max Activating Token Index: 914

Text #15

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0673. Min Act: -0.0002

Data Index: 633725 (C4 (Web Text))

Max Activating Token Index: 661

Text #16

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0702. Min Act: -0.0002

Data Index: 372884 (C4 (Web Text))

Max Activating Token Index: 377

Text #17

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0690. Min Act: -0.0002

Data Index: 668341 (C4 (Web Text))

Max Activating Token Index: 341

Text #18

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0687. Min Act: -0.0002

Data Index: 1301557 (C4 (Web Text))

Max Activating Token Index: 845

Text #19

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0642. Min Act: -0.0002

Data Index: 1168464 (C4 (Web Text))

Max Activating Token Index: 260