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

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

Neuron 1420 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: 0.0926. Min Range: -0.0926

Max Act: 0.0926. Min Act: -0.0002

Data Index: 453389 (C4 (Web Text))

Max Activating Token Index: 994

Text #1

Max Range: 0.0926. Min Range: -0.0926

Max Act: 0.0904. Min Act: -0.0000

Data Index: 434114 (C4 (Web Text))

Max Activating Token Index: 751

Text #2

Max Range: 0.0926. Min Range: -0.0926

Max Act: 0.0826. Min Act: -0.0001

Data Index: 138241 (C4 (Web Text))

Max Activating Token Index: 992

Text #3

Max Range: 0.0926. Min Range: -0.0926

Max Act: 0.0782. Min Act: -0.0002

Data Index: 15313 (C4 (Web Text))

Max Activating Token Index: 334

Text #4

Max Range: 0.0926. Min Range: -0.0926

Max Act: 0.0771. Min Act: -0.0001

Data Index: 1130989 (C4 (Web Text))

Max Activating Token Index: 732

Text #5

Max Range: 0.0926. Min Range: -0.0926

Max Act: 0.0738. Min Act: -0.0001

Data Index: 58264 (C4 (Web Text))

Max Activating Token Index: 558

Text #6

Max Range: 0.0926. Min Range: -0.0926

Max Act: 0.0719. Min Act: -0.0000

Data Index: 566795 (C4 (Web Text))

Max Activating Token Index: 245

Text #7

Max Range: 0.0926. Min Range: -0.0926

Max Act: 0.0720. Min Act: -0.0002

Data Index: 665252 (C4 (Web Text))

Max Activating Token Index: 925

Text #8

Max Range: 0.0926. Min Range: -0.0926

Max Act: 0.0706. Min Act: -0.0001

Data Index: 329379 (C4 (Web Text))

Max Activating Token Index: 568

Text #9

Max Range: 0.0926. Min Range: -0.0926

Max Act: 0.0690. Min Act: -0.0002

Data Index: 660612 (C4 (Web Text))

Max Activating Token Index: 9

Text #10

Max Range: 0.0926. Min Range: -0.0926

Max Act: 0.0695. Min Act: -0.0001

Data Index: 1086573 (C4 (Web Text))

Max Activating Token Index: 47

Text #11

Max Range: 0.0926. Min Range: -0.0926

Max Act: 0.0704. Min Act: -0.0000

Data Index: 137798 (C4 (Web Text))

Max Activating Token Index: 869

Text #12

Max Range: 0.0926. Min Range: -0.0926

Max Act: 0.0690. Min Act: -0.0001

Data Index: 488609 (C4 (Web Text))

Max Activating Token Index: 818

Text #13

Max Range: 0.0926. Min Range: -0.0926

Max Act: 0.0663. Min Act: -0.0001

Data Index: 738394 (C4 (Web Text))

Max Activating Token Index: 546

Text #14

Max Range: 0.0926. Min Range: -0.0926

Max Act: 0.0672. Min Act: -0.0001

Data Index: 473328 (C4 (Web Text))

Max Activating Token Index: 154

Text #15

Max Range: 0.0926. Min Range: -0.0926

Max Act: 0.0680. Min Act: -0.0002

Data Index: 1355622 (C4 (Web Text))

Max Activating Token Index: 8

Text #16

Max Range: 0.0926. Min Range: -0.0926

Max Act: 0.0677. Min Act: -0.0002

Data Index: 485863 (C4 (Web Text))

Max Activating Token Index: 137

Text #17

Max Range: 0.0926. Min Range: -0.0926

Max Act: 0.0660. Min Act: -0.0002

Data Index: 1350657 (C4 (Web Text))

Max Activating Token Index: 583

Text #18

Max Range: 0.0926. Min Range: -0.0926

Max Act: 0.0674. Min Act: -0.0002

Data Index: 847498 (C4 (Web Text))

Max Activating Token Index: 775

Text #19

Max Range: 0.0926. Min Range: -0.0926

Max Act: 0.0665. Min Act: -0.0001

Data Index: 776471 (C4 (Web Text))

Max Activating Token Index: 743