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

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

Neuron 3796 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: 0.0769. Min Range: -0.0769

Max Act: 0.0656. Min Act: -0.0002

Data Index: 1250154 (C4 (Web Text))

Max Activating Token Index: 75

Text #1

Max Range: 0.0769. Min Range: -0.0769

Max Act: 0.0550. Min Act: -0.0002

Data Index: 85358 (C4 (Web Text))

Max Activating Token Index: 200

Text #2

Max Range: 0.0769. Min Range: -0.0769

Max Act: 0.0647. Min Act: -0.0002

Data Index: 1067394 (C4 (Web Text))

Max Activating Token Index: 712

Text #3

Max Range: 0.0769. Min Range: -0.0769

Max Act: 0.0769. Min Act: -0.0002

Data Index: 690466 (C4 (Web Text))

Max Activating Token Index: 712

Text #4

Max Range: 0.0769. Min Range: -0.0769

Max Act: 0.0697. Min Act: -0.0002

Data Index: 1089808 (C4 (Web Text))

Max Activating Token Index: 935

Text #5

Max Range: 0.0769. Min Range: -0.0769

Max Act: 0.0760. Min Act: -0.0002

Data Index: 1091500 (C4 (Web Text))

Max Activating Token Index: 89

Text #6

Max Range: 0.0769. Min Range: -0.0769

Max Act: 0.0659. Min Act: -0.0002

Data Index: 21942 (C4 (Web Text))

Max Activating Token Index: 151

Text #7

Max Range: 0.0769. Min Range: -0.0769

Max Act: 0.0655. Min Act: -0.0002

Data Index: 6762 (C4 (Web Text))

Max Activating Token Index: 806

Text #8

Max Range: 0.0769. Min Range: -0.0769

Max Act: 0.0652. Min Act: -0.0002

Data Index: 517930 (C4 (Web Text))

Max Activating Token Index: 815

Text #9

Max Range: 0.0769. Min Range: -0.0769

Max Act: 0.0672. Min Act: -0.0002

Data Index: 922989 (C4 (Web Text))

Max Activating Token Index: 33

Text #10

Max Range: 0.0769. Min Range: -0.0769

Max Act: 0.0683. Min Act: -0.0002

Data Index: 693738 (C4 (Web Text))

Max Activating Token Index: 156

Text #11

Max Range: 0.0769. Min Range: -0.0769

Max Act: 0.0563. Min Act: -0.0002

Data Index: 323149 (C4 (Web Text))

Max Activating Token Index: 247

Text #12

Max Range: 0.0769. Min Range: -0.0769

Max Act: 0.0723. Min Act: -0.0002

Data Index: 478524 (C4 (Web Text))

Max Activating Token Index: 739

Text #13

Max Range: 0.0769. Min Range: -0.0769

Max Act: 0.0581. Min Act: -0.0002

Data Index: 369530 (C4 (Web Text))

Max Activating Token Index: 680

Text #14

Max Range: 0.0769. Min Range: -0.0769

Max Act: 0.0722. Min Act: -0.0002

Data Index: 1315182 (C4 (Web Text))

Max Activating Token Index: 772

Text #15

Max Range: 0.0769. Min Range: -0.0769

Max Act: 0.0540. Min Act: -0.0002

Data Index: 205946 (C4 (Web Text))

Max Activating Token Index: 118

Text #16

Max Range: 0.0769. Min Range: -0.0769

Max Act: 0.0664. Min Act: -0.0002

Data Index: 539855 (C4 (Web Text))

Max Activating Token Index: 789

Text #17

Max Range: 0.0769. Min Range: -0.0769

Max Act: 0.0593. Min Act: -0.0002

Data Index: 1192920 (C4 (Web Text))

Max Activating Token Index: 777

Text #18

Max Range: 0.0769. Min Range: -0.0769

Max Act: 0.0710. Min Act: -0.0002

Data Index: 963050 (C4 (Web Text))

Max Activating Token Index: 166

Text #19

Max Range: 0.0769. Min Range: -0.0769

Max Act: 0.0613. Min Act: -0.0002

Data Index: 405681 (C4 (Web Text))

Max Activating Token Index: 628