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

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

Neuron 106 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: 0.0767. Min Range: -0.0767

Max Act: 0.0767. Min Act: -0.0001

Data Index: 844076 (C4 (Web Text))

Max Activating Token Index: 446

Text #1

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0688. Min Act: -0.0002

Data Index: 999137 (C4 (Web Text))

Max Activating Token Index: 695

Text #2

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0694. Min Act: -0.0002

Data Index: 1225462 (C4 (Web Text))

Max Activating Token Index: 620

Text #3

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0689. Min Act: -0.0002

Data Index: 374965 (C4 (Web Text))

Max Activating Token Index: 759

Text #4

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0695. Min Act: -0.0002

Data Index: 859470 (C4 (Web Text))

Max Activating Token Index: 252

Text #5

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0687. Min Act: -0.0002

Data Index: 1308071 (C4 (Web Text))

Max Activating Token Index: 665

Text #6

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0680. Min Act: -0.0002

Data Index: 179540 (C4 (Web Text))

Max Activating Token Index: 58

Text #7

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0672. Min Act: -0.0002

Data Index: 321197 (C4 (Web Text))

Max Activating Token Index: 766

Text #8

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0660. Min Act: -0.0002

Data Index: 257556 (C4 (Web Text))

Max Activating Token Index: 364

Text #9

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0624. Min Act: -0.0002

Data Index: 1354586 (C4 (Web Text))

Max Activating Token Index: 280

Text #10

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0657. Min Act: -0.0002

Data Index: 457793 (C4 (Web Text))

Max Activating Token Index: 433

Text #11

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0634. Min Act: -0.0002

Data Index: 245728 (C4 (Web Text))

Max Activating Token Index: 123

Text #12

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0663. Min Act: -0.0002

Data Index: 515674 (C4 (Web Text))

Max Activating Token Index: 241

Text #13

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0660. Min Act: -0.0002

Data Index: 736296 (C4 (Web Text))

Max Activating Token Index: 344

Text #14

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0630. Min Act: -0.0002

Data Index: 1061873 (C4 (Web Text))

Max Activating Token Index: 69

Text #15

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0640. Min Act: -0.0002

Data Index: 1312912 (C4 (Web Text))

Max Activating Token Index: 122

Text #16

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0605. Min Act: -0.0002

Data Index: 103194 (C4 (Web Text))

Max Activating Token Index: 266

Text #17

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0620. Min Act: -0.0002

Data Index: 1253016 (C4 (Web Text))

Max Activating Token Index: 468

Text #18

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0610. Min Act: -0.0002

Data Index: 439746 (C4 (Web Text))

Max Activating Token Index: 822

Text #19

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0622. Min Act: -0.0002

Data Index: 40776 (C4 (Web Text))

Max Activating Token Index: 603