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

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

Neuron 964 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: 0.1016. Min Range: -0.1016

Max Act: 0.1016. Min Act: -0.0002

Data Index: 451272 (C4 (Web Text))

Max Activating Token Index: 327

Text #1

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0907. Min Act: -0.0001

Data Index: 47878 (C4 (Web Text))

Max Activating Token Index: 550

Text #2

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0826. Min Act: -0.0002

Data Index: 314822 (C4 (Web Text))

Max Activating Token Index: 823

Text #3

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0873. Min Act: -0.0002

Data Index: 1383581 (Python Code)

Max Activating Token Index: 928

Text #4

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0841. Min Act: -0.0002

Data Index: 1529567 (Python Code)

Max Activating Token Index: 732

Text #5

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0816. Min Act: -0.0001

Data Index: 921074 (C4 (Web Text))

Max Activating Token Index: 92

Text #6

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0688. Min Act: -0.0002

Data Index: 967797 (C4 (Web Text))

Max Activating Token Index: 920

Text #7

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0680. Min Act: -0.0001

Data Index: 685469 (C4 (Web Text))

Max Activating Token Index: 777

Text #8

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0672. Min Act: -0.0002

Data Index: 1209376 (C4 (Web Text))

Max Activating Token Index: 116

Text #9

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0689. Min Act: -0.0002

Data Index: 469103 (C4 (Web Text))

Max Activating Token Index: 880

Text #10

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0688. Min Act: -0.0002

Data Index: 365931 (C4 (Web Text))

Max Activating Token Index: 647

Text #11

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0663. Min Act: -0.0001

Data Index: 193887 (C4 (Web Text))

Max Activating Token Index: 824

Text #12

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0663. Min Act: -0.0002

Data Index: 869416 (C4 (Web Text))

Max Activating Token Index: 775

Text #13

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0597. Min Act: -0.0002

Data Index: 1218686 (C4 (Web Text))

Max Activating Token Index: 877

Text #14

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0636. Min Act: -0.0001

Data Index: 457303 (C4 (Web Text))

Max Activating Token Index: 653

Text #15

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0648. Min Act: -0.0001

Data Index: 669267 (C4 (Web Text))

Max Activating Token Index: 547

Text #16

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0636. Min Act: -0.0002

Data Index: 433632 (C4 (Web Text))

Max Activating Token Index: 599

Text #17

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0750. Min Act: -0.0002

Data Index: 422869 (C4 (Web Text))

Max Activating Token Index: 99

Text #18

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0656. Min Act: -0.0001

Data Index: 323475 (C4 (Web Text))

Max Activating Token Index: 959

Text #19

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0583. Min Act: -0.0002

Data Index: 1411172 (Python Code)

Max Activating Token Index: 233