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

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

Neuron 2403 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: 0.0915. Min Range: -0.0915

Max Act: 0.0915. Min Act: -0.0001

Data Index: 34669 (C4 (Web Text))

Max Activating Token Index: 905

Text #1

Max Range: 0.0915. Min Range: -0.0915

Max Act: 0.0834. Min Act: -0.0001

Data Index: 412577 (C4 (Web Text))

Max Activating Token Index: 629

Text #2

Max Range: 0.0915. Min Range: -0.0915

Max Act: 0.0764. Min Act: -0.0001

Data Index: 430895 (C4 (Web Text))

Max Activating Token Index: 760

Text #3

Max Range: 0.0915. Min Range: -0.0915

Max Act: 0.0827. Min Act: -0.0001

Data Index: 323844 (C4 (Web Text))

Max Activating Token Index: 608

Text #4

Max Range: 0.0915. Min Range: -0.0915

Max Act: 0.0751. Min Act: -0.0001

Data Index: 446901 (C4 (Web Text))

Max Activating Token Index: 829

Text #5

Max Range: 0.0915. Min Range: -0.0915

Max Act: 0.0786. Min Act: -0.0001

Data Index: 1235733 (C4 (Web Text))

Max Activating Token Index: 496

Text #6

Max Range: 0.0915. Min Range: -0.0915

Max Act: 0.0758. Min Act: -0.0001

Data Index: 1138471 (C4 (Web Text))

Max Activating Token Index: 496

Text #7

Max Range: 0.0915. Min Range: -0.0915

Max Act: 0.0739. Min Act: -0.0001

Data Index: 541189 (C4 (Web Text))

Max Activating Token Index: 498

Text #8

Max Range: 0.0915. Min Range: -0.0915

Max Act: 0.0719. Min Act: -0.0001

Data Index: 565679 (C4 (Web Text))

Max Activating Token Index: 512

Text #9

Max Range: 0.0915. Min Range: -0.0915

Max Act: 0.0687. Min Act: -0.0001

Data Index: 801129 (C4 (Web Text))

Max Activating Token Index: 981

Text #10

Max Range: 0.0915. Min Range: -0.0915

Max Act: 0.0705. Min Act: -0.0001

Data Index: 1011773 (C4 (Web Text))

Max Activating Token Index: 622

Text #11

Max Range: 0.0915. Min Range: -0.0915

Max Act: 0.0722. Min Act: -0.0001

Data Index: 1376562 (Python Code)

Max Activating Token Index: 334

Text #12

Max Range: 0.0915. Min Range: -0.0915

Max Act: 0.0697. Min Act: -0.0001

Data Index: 871394 (C4 (Web Text))

Max Activating Token Index: 452

Text #13

Max Range: 0.0915. Min Range: -0.0915

Max Act: 0.0691. Min Act: -0.0001

Data Index: 1449040 (Python Code)

Max Activating Token Index: 855

Text #14

Max Range: 0.0915. Min Range: -0.0915

Max Act: 0.0679. Min Act: -0.0001

Data Index: 438717 (C4 (Web Text))

Max Activating Token Index: 1014

Text #15

Max Range: 0.0915. Min Range: -0.0915

Max Act: 0.0663. Min Act: -0.0001

Data Index: 1655959 (Python Code)

Max Activating Token Index: 458

Text #16

Max Range: 0.0915. Min Range: -0.0915

Max Act: 0.0660. Min Act: -0.0001

Data Index: 817446 (C4 (Web Text))

Max Activating Token Index: 481

Text #17

Max Range: 0.0915. Min Range: -0.0915

Max Act: 0.0693. Min Act: -0.0001

Data Index: 1256379 (C4 (Web Text))

Max Activating Token Index: 865

Text #18

Max Range: 0.0915. Min Range: -0.0915

Max Act: 0.0663. Min Act: -0.0001

Data Index: 251058 (C4 (Web Text))

Max Activating Token Index: 674

Text #19

Max Range: 0.0915. Min Range: -0.0915

Max Act: 0.0688. Min Act: -0.0001

Data Index: 1555506 (Python Code)

Max Activating Token Index: 437