Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 375 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2276. Min Range: -0.2276

Max Act: 0.2276. Min Act: -0.0001

Data Index: 737564 (C4 (Web Text))

Max Activating Token Index: 703

Text #1

Max Range: 0.2276. Min Range: -0.2276

Max Act: 0.2047. Min Act: -0.0001

Data Index: 1248732 (C4 (Web Text))

Max Activating Token Index: 53

Text #2

Max Range: 0.2276. Min Range: -0.2276

Max Act: 0.2036. Min Act: -0.0001

Data Index: 238369 (C4 (Web Text))

Max Activating Token Index: 621

Text #3

Max Range: 0.2276. Min Range: -0.2276

Max Act: 0.1882. Min Act: -0.0001

Data Index: 761079 (C4 (Web Text))

Max Activating Token Index: 965

Text #4

Max Range: 0.2276. Min Range: -0.2276

Max Act: 0.1847. Min Act: -0.0001

Data Index: 565877 (C4 (Web Text))

Max Activating Token Index: 78

Text #5

Max Range: 0.2276. Min Range: -0.2276

Max Act: 0.1794. Min Act: -0.0001

Data Index: 422988 (C4 (Web Text))

Max Activating Token Index: 769

Text #6

Max Range: 0.2276. Min Range: -0.2276

Max Act: 0.1783. Min Act: -0.0001

Data Index: 1075850 (C4 (Web Text))

Max Activating Token Index: 860

Text #7

Max Range: 0.2276. Min Range: -0.2276

Max Act: 0.1678. Min Act: -0.0001

Data Index: 927038 (C4 (Web Text))

Max Activating Token Index: 143

Text #8

Max Range: 0.2276. Min Range: -0.2276

Max Act: 0.1714. Min Act: -0.0001

Data Index: 1046216 (C4 (Web Text))

Max Activating Token Index: 280

Text #9

Max Range: 0.2276. Min Range: -0.2276

Max Act: 0.1623. Min Act: -0.0001

Data Index: 698985 (C4 (Web Text))

Max Activating Token Index: 291

Text #10

Max Range: 0.2276. Min Range: -0.2276

Max Act: 0.1673. Min Act: -0.0001

Data Index: 586451 (C4 (Web Text))

Max Activating Token Index: 946

Text #11

Max Range: 0.2276. Min Range: -0.2276

Max Act: 0.1619. Min Act: -0.0001

Data Index: 832774 (C4 (Web Text))

Max Activating Token Index: 710

Text #12

Max Range: 0.2276. Min Range: -0.2276

Max Act: 0.1584. Min Act: -0.0001

Data Index: 1202512 (C4 (Web Text))

Max Activating Token Index: 724

Text #13

Max Range: 0.2276. Min Range: -0.2276

Max Act: 0.1614. Min Act: -0.0001

Data Index: 994214 (C4 (Web Text))

Max Activating Token Index: 785

Text #14

Max Range: 0.2276. Min Range: -0.2276

Max Act: 0.1519. Min Act: -0.0001

Data Index: 504865 (C4 (Web Text))

Max Activating Token Index: 794

Text #15

Max Range: 0.2276. Min Range: -0.2276

Max Act: 0.1576. Min Act: -0.0001

Data Index: 1258475 (C4 (Web Text))

Max Activating Token Index: 587

Text #16

Max Range: 0.2276. Min Range: -0.2276

Max Act: 0.1487. Min Act: -0.0001

Data Index: 234997 (C4 (Web Text))

Max Activating Token Index: 578

Text #17

Max Range: 0.2276. Min Range: -0.2276

Max Act: 0.1608. Min Act: -0.0001

Data Index: 35566 (C4 (Web Text))

Max Activating Token Index: 845

Text #18

Max Range: 0.2276. Min Range: -0.2276

Max Act: 0.1594. Min Act: -0.0001

Data Index: 434990 (C4 (Web Text))

Max Activating Token Index: 134

Text #19

Max Range: 0.2276. Min Range: -0.2276

Max Act: 0.1572. Min Act: -0.0001

Data Index: 393738 (C4 (Web Text))

Max Activating Token Index: 979