Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3667 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3217. Min Range: -0.3217

Max Act: 0.3217. Min Act: -0.0001

Data Index: 1129255 (C4 (Web Text))

Max Activating Token Index: 511

Text #1

Max Range: 0.3217. Min Range: -0.3217

Max Act: 0.1778. Min Act: -0.0001

Data Index: 487084 (C4 (Web Text))

Max Activating Token Index: 287

Text #2

Max Range: 0.3217. Min Range: -0.3217

Max Act: 0.1880. Min Act: -0.0001

Data Index: 633207 (C4 (Web Text))

Max Activating Token Index: 808

Text #3

Max Range: 0.3217. Min Range: -0.3217

Max Act: 0.1698. Min Act: -0.0001

Data Index: 249219 (C4 (Web Text))

Max Activating Token Index: 958

Text #4

Max Range: 0.3217. Min Range: -0.3217

Max Act: 0.1736. Min Act: -0.0001

Data Index: 832138 (C4 (Web Text))

Max Activating Token Index: 108

Text #5

Max Range: 0.3217. Min Range: -0.3217

Max Act: 0.1782. Min Act: -0.0001

Data Index: 751384 (C4 (Web Text))

Max Activating Token Index: 6

Text #6

Max Range: 0.3217. Min Range: -0.3217

Max Act: 0.1792. Min Act: -0.0001

Data Index: 483635 (C4 (Web Text))

Max Activating Token Index: 914

Text #7

Max Range: 0.3217. Min Range: -0.3217

Max Act: 0.1758. Min Act: -0.0001

Data Index: 541620 (C4 (Web Text))

Max Activating Token Index: 165

Text #8

Max Range: 0.3217. Min Range: -0.3217

Max Act: 0.1751. Min Act: -0.0001

Data Index: 1007488 (C4 (Web Text))

Max Activating Token Index: 199

Text #9

Max Range: 0.3217. Min Range: -0.3217

Max Act: 0.1693. Min Act: -0.0001

Data Index: 938455 (C4 (Web Text))

Max Activating Token Index: 823

Text #10

Max Range: 0.3217. Min Range: -0.3217

Max Act: 0.1749. Min Act: -0.0001

Data Index: 448720 (C4 (Web Text))

Max Activating Token Index: 560

Text #11

Max Range: 0.3217. Min Range: -0.3217

Max Act: 0.1743. Min Act: -0.0001

Data Index: 669481 (C4 (Web Text))

Max Activating Token Index: 124

Text #12

Max Range: 0.3217. Min Range: -0.3217

Max Act: 0.1798. Min Act: -0.0001

Data Index: 125877 (C4 (Web Text))

Max Activating Token Index: 129

Text #13

Max Range: 0.3217. Min Range: -0.3217

Max Act: 0.1676. Min Act: -0.0001

Data Index: 31216 (C4 (Web Text))

Max Activating Token Index: 270

Text #14

Max Range: 0.3217. Min Range: -0.3217

Max Act: 0.1727. Min Act: -0.0001

Data Index: 132404 (C4 (Web Text))

Max Activating Token Index: 76

Text #15

Max Range: 0.3217. Min Range: -0.3217

Max Act: 0.1706. Min Act: -0.0001

Data Index: 612947 (C4 (Web Text))

Max Activating Token Index: 475

Text #16

Max Range: 0.3217. Min Range: -0.3217

Max Act: 0.1647. Min Act: -0.0001

Data Index: 1038779 (C4 (Web Text))

Max Activating Token Index: 739

Text #17

Max Range: 0.3217. Min Range: -0.3217

Max Act: 0.1707. Min Act: -0.0001

Data Index: 1088874 (C4 (Web Text))

Max Activating Token Index: 717

Text #18

Max Range: 0.3217. Min Range: -0.3217

Max Act: 0.1694. Min Act: -0.0001

Data Index: 299457 (C4 (Web Text))

Max Activating Token Index: 556

Text #19

Max Range: 0.3217. Min Range: -0.3217

Max Act: 0.1686. Min Act: -0.0001

Data Index: 745639 (C4 (Web Text))

Max Activating Token Index: 39