Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2387 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0990. Min Range: -0.0990

Max Act: 0.0954. Min Act: -0.0002

Data Index: 1512921 (Python Code)

Max Activating Token Index: 521

Text #1

Max Range: 0.0990. Min Range: -0.0990

Max Act: 0.0990. Min Act: -0.0002

Data Index: 1562148 (Python Code)

Max Activating Token Index: 108

Text #2

Max Range: 0.0990. Min Range: -0.0990

Max Act: 0.0840. Min Act: -0.0002

Data Index: 1640764 (Python Code)

Max Activating Token Index: 335

Text #3

Max Range: 0.0990. Min Range: -0.0990

Max Act: 0.0759. Min Act: -0.0002

Data Index: 1424392 (Python Code)

Max Activating Token Index: 566

Text #4

Max Range: 0.0990. Min Range: -0.0990

Max Act: 0.0770. Min Act: -0.0002

Data Index: 801117 (C4 (Web Text))

Max Activating Token Index: 661

Text #5

Max Range: 0.0990. Min Range: -0.0990

Max Act: 0.0800. Min Act: -0.0002

Data Index: 1473986 (Python Code)

Max Activating Token Index: 872

Text #6

Max Range: 0.0990. Min Range: -0.0990

Max Act: 0.0875. Min Act: -0.0002

Data Index: 753997 (C4 (Web Text))

Max Activating Token Index: 762

Text #7

Max Range: 0.0990. Min Range: -0.0990

Max Act: 0.0848. Min Act: -0.0002

Data Index: 1614302 (Python Code)

Max Activating Token Index: 106

Text #8

Max Range: 0.0990. Min Range: -0.0990

Max Act: 0.0776. Min Act: -0.0002

Data Index: 1620774 (Python Code)

Max Activating Token Index: 637

Text #9

Max Range: 0.0990. Min Range: -0.0990

Max Act: 0.0800. Min Act: -0.0002

Data Index: 1439320 (Python Code)

Max Activating Token Index: 594

Text #10

Max Range: 0.0990. Min Range: -0.0990

Max Act: 0.0810. Min Act: -0.0002

Data Index: 1513662 (Python Code)

Max Activating Token Index: 536

Text #11

Max Range: 0.0990. Min Range: -0.0990

Max Act: 0.0717. Min Act: -0.0002

Data Index: 1251954 (C4 (Web Text))

Max Activating Token Index: 144

Text #12

Max Range: 0.0990. Min Range: -0.0990

Max Act: 0.0792. Min Act: -0.0002

Data Index: 1543229 (Python Code)

Max Activating Token Index: 710

Text #13

Max Range: 0.0990. Min Range: -0.0990

Max Act: 0.0729. Min Act: -0.0002

Data Index: 1016133 (C4 (Web Text))

Max Activating Token Index: 505

Text #14

Max Range: 0.0990. Min Range: -0.0990

Max Act: 0.0760. Min Act: -0.0002

Data Index: 1055313 (C4 (Web Text))

Max Activating Token Index: 58

Text #15

Max Range: 0.0990. Min Range: -0.0990

Max Act: 0.0733. Min Act: -0.0002

Data Index: 1648939 (Python Code)

Max Activating Token Index: 472

Text #16

Max Range: 0.0990. Min Range: -0.0990

Max Act: 0.0690. Min Act: -0.0002

Data Index: 1554467 (Python Code)

Max Activating Token Index: 180

Text #17

Max Range: 0.0990. Min Range: -0.0990

Max Act: 0.0787. Min Act: -0.0002

Data Index: 1452716 (Python Code)

Max Activating Token Index: 227

Text #18

Max Range: 0.0990. Min Range: -0.0990

Max Act: 0.0686. Min Act: -0.0002

Data Index: 327413 (C4 (Web Text))

Max Activating Token Index: 539

Text #19

Max Range: 0.0990. Min Range: -0.0990

Max Act: 0.0679. Min Act: -0.0002

Data Index: 491791 (C4 (Web Text))

Max Activating Token Index: 305