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

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

Neuron 861 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0807. Min Act: -0.0002

Data Index: 1093716 (C4 (Web Text))

Max Activating Token Index: 2

Text #1

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0773. Min Act: -0.0002

Data Index: 323138 (C4 (Web Text))

Max Activating Token Index: 2

Text #2

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0773. Min Act: -0.0002

Data Index: 1500347 (Python Code)

Max Activating Token Index: 2

Text #3

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0773. Min Act: -0.0002

Data Index: 1574608 (Python Code)

Max Activating Token Index: 2

Text #4

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0773. Min Act: -0.0002

Data Index: 1582255 (Python Code)

Max Activating Token Index: 2

Text #5

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0773. Min Act: -0.0002

Data Index: 1520729 (Python Code)

Max Activating Token Index: 2

Text #6

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0773. Min Act: -0.0002

Data Index: 1625123 (Python Code)

Max Activating Token Index: 2

Text #7

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0773. Min Act: -0.0002

Data Index: 1283269 (C4 (Web Text))

Max Activating Token Index: 2

Text #8

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0762. Min Act: -0.0002

Data Index: 1644792 (Python Code)

Max Activating Token Index: 3

Text #9

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0693. Min Act: -0.0002

Data Index: 1566735 (Python Code)

Max Activating Token Index: 4

Text #10

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0596. Min Act: -0.0002

Data Index: 94759 (C4 (Web Text))

Max Activating Token Index: 3

Text #11

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0587. Min Act: -0.0002

Data Index: 1164227 (C4 (Web Text))

Max Activating Token Index: 2

Text #12

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0587. Min Act: -0.0002

Data Index: 430531 (C4 (Web Text))

Max Activating Token Index: 2

Text #13

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0587. Min Act: -0.0002

Data Index: 765611 (C4 (Web Text))

Max Activating Token Index: 2

Text #14

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0587. Min Act: -0.0002

Data Index: 1631648 (Python Code)

Max Activating Token Index: 2

Text #15

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0562. Min Act: -0.0002

Data Index: 1510735 (Python Code)

Max Activating Token Index: 3

Text #16

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0546. Min Act: -0.0002

Data Index: 1446075 (Python Code)

Max Activating Token Index: 7

Text #17

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0540. Min Act: -0.0002

Data Index: 1506790 (Python Code)

Max Activating Token Index: 4

Text #18

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0535. Min Act: -0.0002

Data Index: 1636456 (Python Code)

Max Activating Token Index: 7

Text #19

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0520. Min Act: -0.0002

Data Index: 1411428 (Python Code)

Max Activating Token Index: 4