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

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

Neuron 3210 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: 0.0855. Min Range: -0.0855

Max Act: 0.0846. Min Act: -0.0002

Data Index: 561907 (C4 (Web Text))

Max Activating Token Index: 6

Text #1

Max Range: 0.0855. Min Range: -0.0855

Max Act: 0.0855. Min Act: -0.0002

Data Index: 1318516 (C4 (Web Text))

Max Activating Token Index: 830

Text #2

Max Range: 0.0855. Min Range: -0.0855

Max Act: 0.0699. Min Act: -0.0002

Data Index: 707729 (C4 (Web Text))

Max Activating Token Index: 103

Text #3

Max Range: 0.0855. Min Range: -0.0855

Max Act: 0.0726. Min Act: -0.0002

Data Index: 884854 (C4 (Web Text))

Max Activating Token Index: 174

Text #4

Max Range: 0.0855. Min Range: -0.0855

Max Act: 0.0706. Min Act: -0.0002

Data Index: 920612 (C4 (Web Text))

Max Activating Token Index: 831

Text #5

Max Range: 0.0855. Min Range: -0.0855

Max Act: 0.0676. Min Act: -0.0002

Data Index: 378685 (C4 (Web Text))

Max Activating Token Index: 723

Text #6

Max Range: 0.0855. Min Range: -0.0855

Max Act: 0.0751. Min Act: -0.0002

Data Index: 515455 (C4 (Web Text))

Max Activating Token Index: 153

Text #7

Max Range: 0.0855. Min Range: -0.0855

Max Act: 0.0691. Min Act: -0.0002

Data Index: 880593 (C4 (Web Text))

Max Activating Token Index: 39

Text #8

Max Range: 0.0855. Min Range: -0.0855

Max Act: 0.0683. Min Act: -0.0002

Data Index: 587644 (C4 (Web Text))

Max Activating Token Index: 382

Text #9

Max Range: 0.0855. Min Range: -0.0855

Max Act: 0.0643. Min Act: -0.0002

Data Index: 164507 (C4 (Web Text))

Max Activating Token Index: 23

Text #10

Max Range: 0.0855. Min Range: -0.0855

Max Act: 0.0694. Min Act: -0.0002

Data Index: 604101 (C4 (Web Text))

Max Activating Token Index: 295

Text #11

Max Range: 0.0855. Min Range: -0.0855

Max Act: 0.0673. Min Act: -0.0002

Data Index: 118739 (C4 (Web Text))

Max Activating Token Index: 530

Text #12

Max Range: 0.0855. Min Range: -0.0855

Max Act: 0.0676. Min Act: -0.0002

Data Index: 55891 (C4 (Web Text))

Max Activating Token Index: 306

Text #13

Max Range: 0.0855. Min Range: -0.0855

Max Act: 0.0649. Min Act: -0.0002

Data Index: 1078815 (C4 (Web Text))

Max Activating Token Index: 38

Text #14

Max Range: 0.0855. Min Range: -0.0855

Max Act: 0.0722. Min Act: -0.0002

Data Index: 1176990 (C4 (Web Text))

Max Activating Token Index: 16

Text #15

Max Range: 0.0855. Min Range: -0.0855

Max Act: 0.0644. Min Act: -0.0002

Data Index: 1324751 (C4 (Web Text))

Max Activating Token Index: 7

Text #16

Max Range: 0.0855. Min Range: -0.0855

Max Act: 0.0625. Min Act: -0.0002

Data Index: 1060477 (C4 (Web Text))

Max Activating Token Index: 321

Text #17

Max Range: 0.0855. Min Range: -0.0855

Max Act: 0.0633. Min Act: -0.0002

Data Index: 477811 (C4 (Web Text))

Max Activating Token Index: 329

Text #18

Max Range: 0.0855. Min Range: -0.0855

Max Act: 0.0683. Min Act: -0.0002

Data Index: 723427 (C4 (Web Text))

Max Activating Token Index: 175

Text #19

Max Range: 0.0855. Min Range: -0.0855

Max Act: 0.0631. Min Act: -0.0002

Data Index: 1286722 (C4 (Web Text))

Max Activating Token Index: 5