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

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

Neuron 538 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: 0.0788. Min Range: -0.0788

Max Act: 0.0788. Min Act: -0.0002

Data Index: 1007812 (C4 (Web Text))

Max Activating Token Index: 725

Text #1

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0761. Min Act: -0.0002

Data Index: 895730 (C4 (Web Text))

Max Activating Token Index: 780

Text #2

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0743. Min Act: -0.0002

Data Index: 608677 (C4 (Web Text))

Max Activating Token Index: 808

Text #3

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0682. Min Act: -0.0002

Data Index: 771526 (C4 (Web Text))

Max Activating Token Index: 125

Text #4

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0667. Min Act: -0.0002

Data Index: 116707 (C4 (Web Text))

Max Activating Token Index: 296

Text #5

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0688. Min Act: -0.0002

Data Index: 357551 (C4 (Web Text))

Max Activating Token Index: 747

Text #6

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0666. Min Act: -0.0002

Data Index: 113150 (C4 (Web Text))

Max Activating Token Index: 540

Text #7

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0675. Min Act: -0.0002

Data Index: 695378 (C4 (Web Text))

Max Activating Token Index: 234

Text #8

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0687. Min Act: -0.0002

Data Index: 103585 (C4 (Web Text))

Max Activating Token Index: 816

Text #9

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0672. Min Act: -0.0002

Data Index: 399713 (C4 (Web Text))

Max Activating Token Index: 797

Text #10

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0655. Min Act: -0.0002

Data Index: 213406 (C4 (Web Text))

Max Activating Token Index: 866

Text #11

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0672. Min Act: -0.0002

Data Index: 637270 (C4 (Web Text))

Max Activating Token Index: 498

Text #12

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0671. Min Act: -0.0002

Data Index: 12395 (C4 (Web Text))

Max Activating Token Index: 678

Text #13

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0663. Min Act: -0.0002

Data Index: 1019010 (C4 (Web Text))

Max Activating Token Index: 417

Text #14

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0667. Min Act: -0.0002

Data Index: 849048 (C4 (Web Text))

Max Activating Token Index: 357

Text #15

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0677. Min Act: -0.0002

Data Index: 868143 (C4 (Web Text))

Max Activating Token Index: 636

Text #16

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0658. Min Act: -0.0002

Data Index: 786267 (C4 (Web Text))

Max Activating Token Index: 886

Text #17

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0642. Min Act: -0.0002

Data Index: 747045 (C4 (Web Text))

Max Activating Token Index: 520

Text #18

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0649. Min Act: -0.0002

Data Index: 655773 (C4 (Web Text))

Max Activating Token Index: 214

Text #19

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0662. Min Act: -0.0002

Data Index: 827695 (C4 (Web Text))

Max Activating Token Index: 476