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

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

Neuron 807 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: 0.0850. Min Range: -0.0850

Max Act: 0.0850. Min Act: -0.0001

Data Index: 332319 (C4 (Web Text))

Max Activating Token Index: 759

Text #1

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0815. Min Act: -0.0001

Data Index: 686066 (C4 (Web Text))

Max Activating Token Index: 613

Text #2

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0815. Min Act: -0.0002

Data Index: 1068324 (C4 (Web Text))

Max Activating Token Index: 709

Text #3

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0776. Min Act: -0.0001

Data Index: 954391 (C4 (Web Text))

Max Activating Token Index: 803

Text #4

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0780. Min Act: -0.0002

Data Index: 872144 (C4 (Web Text))

Max Activating Token Index: 695

Text #5

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0686. Min Act: -0.0002

Data Index: 465741 (C4 (Web Text))

Max Activating Token Index: 330

Text #6

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0691. Min Act: -0.0002

Data Index: 533556 (C4 (Web Text))

Max Activating Token Index: 826

Text #7

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0688. Min Act: -0.0002

Data Index: 367759 (C4 (Web Text))

Max Activating Token Index: 753

Text #8

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0693. Min Act: -0.0001

Data Index: 1157562 (C4 (Web Text))

Max Activating Token Index: 336

Text #9

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0670. Min Act: -0.0001

Data Index: 739900 (C4 (Web Text))

Max Activating Token Index: 418

Text #10

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0698. Min Act: -0.0002

Data Index: 647018 (C4 (Web Text))

Max Activating Token Index: 973

Text #11

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0695. Min Act: -0.0002

Data Index: 591889 (C4 (Web Text))

Max Activating Token Index: 547

Text #12

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0679. Min Act: -0.0002

Data Index: 55104 (C4 (Web Text))

Max Activating Token Index: 620

Text #13

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0630. Min Act: -0.0002

Data Index: 481179 (C4 (Web Text))

Max Activating Token Index: 341

Text #14

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0636. Min Act: -0.0002

Data Index: 7471 (C4 (Web Text))

Max Activating Token Index: 668

Text #15

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0636. Min Act: -0.0002

Data Index: 52219 (C4 (Web Text))

Max Activating Token Index: 406

Text #16

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0631. Min Act: -0.0001

Data Index: 684401 (C4 (Web Text))

Max Activating Token Index: 330

Text #17

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0668. Min Act: -0.0002

Data Index: 85927 (C4 (Web Text))

Max Activating Token Index: 1011

Text #18

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0622. Min Act: -0.0002

Data Index: 953194 (C4 (Web Text))

Max Activating Token Index: 899

Text #19

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0600. Min Act: -0.0002

Data Index: 383938 (C4 (Web Text))

Max Activating Token Index: 430