Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4838 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0785. Min Act: -0.0002

Data Index: 660240 (C4 (Web Text))

Max Activating Token Index: 385

Text #1

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0813. Min Act: -0.0002

Data Index: 1325798 (C4 (Web Text))

Max Activating Token Index: 686

Text #2

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0815. Min Act: -0.0002

Data Index: 761291 (C4 (Web Text))

Max Activating Token Index: 85

Text #3

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0809. Min Act: -0.0002

Data Index: 1331600 (C4 (Web Text))

Max Activating Token Index: 692

Text #4

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0782. Min Act: -0.0002

Data Index: 459947 (C4 (Web Text))

Max Activating Token Index: 642

Text #5

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0774. Min Act: -0.0002

Data Index: 1069964 (C4 (Web Text))

Max Activating Token Index: 727

Text #6

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0771. Min Act: -0.0002

Data Index: 22186 (C4 (Web Text))

Max Activating Token Index: 914

Text #7

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0767. Min Act: -0.0002

Data Index: 1093155 (C4 (Web Text))

Max Activating Token Index: 132

Text #8

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0736. Min Act: -0.0002

Data Index: 98476 (C4 (Web Text))

Max Activating Token Index: 882

Text #9

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0731. Min Act: -0.0002

Data Index: 1037613 (C4 (Web Text))

Max Activating Token Index: 759

Text #10

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0754. Min Act: -0.0002

Data Index: 692933 (C4 (Web Text))

Max Activating Token Index: 447

Text #11

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0756. Min Act: -0.0002

Data Index: 803331 (C4 (Web Text))

Max Activating Token Index: 60

Text #12

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0721. Min Act: -0.0002

Data Index: 92296 (C4 (Web Text))

Max Activating Token Index: 749

Text #13

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0740. Min Act: -0.0002

Data Index: 674343 (C4 (Web Text))

Max Activating Token Index: 558

Text #14

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0739. Min Act: -0.0002

Data Index: 192258 (C4 (Web Text))

Max Activating Token Index: 789

Text #15

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0734. Min Act: -0.0002

Data Index: 1224202 (C4 (Web Text))

Max Activating Token Index: 887

Text #16

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0736. Min Act: -0.0002

Data Index: 459216 (C4 (Web Text))

Max Activating Token Index: 868

Text #17

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0732. Min Act: -0.0002

Data Index: 1026538 (C4 (Web Text))

Max Activating Token Index: 499

Text #18

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0702. Min Act: -0.0002

Data Index: 1332330 (C4 (Web Text))

Max Activating Token Index: 755

Text #19

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0726. Min Act: -0.0002

Data Index: 764118 (C4 (Web Text))

Max Activating Token Index: 607