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

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

Neuron 776 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7634. Min Range: -0.7634

Max Act: 0.7634. Min Act: -0.0000

Data Index: 1573219 (Python Code)

Max Activating Token Index: 659

Text #1

Max Range: 0.7634. Min Range: -0.7634

Max Act: 0.7112. Min Act: -0.0000

Data Index: 1642914 (Python Code)

Max Activating Token Index: 644

Text #2

Max Range: 0.7634. Min Range: -0.7634

Max Act: 0.6825. Min Act: -0.0000

Data Index: 1519398 (Python Code)

Max Activating Token Index: 645

Text #3

Max Range: 0.7634. Min Range: -0.7634

Max Act: 0.5685. Min Act: -0.0000

Data Index: 1560930 (Python Code)

Max Activating Token Index: 160

Text #4

Max Range: 0.7634. Min Range: -0.7634

Max Act: 0.6512. Min Act: -0.0000

Data Index: 1425403 (Python Code)

Max Activating Token Index: 228

Text #5

Max Range: 0.7634. Min Range: -0.7634

Max Act: 0.6088. Min Act: -0.0000

Data Index: 1407751 (Python Code)

Max Activating Token Index: 182

Text #6

Max Range: 0.7634. Min Range: -0.7634

Max Act: 0.5801. Min Act: -0.0000

Data Index: 1608475 (Python Code)

Max Activating Token Index: 795

Text #7

Max Range: 0.7634. Min Range: -0.7634

Max Act: 0.6134. Min Act: -0.0000

Data Index: 1434447 (Python Code)

Max Activating Token Index: 1010

Text #8

Max Range: 0.7634. Min Range: -0.7634

Max Act: 0.5772. Min Act: -0.0000

Data Index: 1378788 (Python Code)

Max Activating Token Index: 507

Text #9

Max Range: 0.7634. Min Range: -0.7634

Max Act: 0.5926. Min Act: -0.0000

Data Index: 1516203 (Python Code)

Max Activating Token Index: 43

Text #10

Max Range: 0.7634. Min Range: -0.7634

Max Act: 0.5609. Min Act: -0.0000

Data Index: 1489941 (Python Code)

Max Activating Token Index: 895

Text #11

Max Range: 0.7634. Min Range: -0.7634

Max Act: 0.5619. Min Act: -0.0000

Data Index: 1606211 (Python Code)

Max Activating Token Index: 162

Text #12

Max Range: 0.7634. Min Range: -0.7634

Max Act: 0.6201. Min Act: -0.0000

Data Index: 1470916 (Python Code)

Max Activating Token Index: 253

Text #13

Max Range: 0.7634. Min Range: -0.7634

Max Act: 0.5794. Min Act: -0.0000

Data Index: 1457643 (Python Code)

Max Activating Token Index: 251

Text #14

Max Range: 0.7634. Min Range: -0.7634

Max Act: 0.6112. Min Act: -0.0000

Data Index: 1600219 (Python Code)

Max Activating Token Index: 806

Text #15

Max Range: 0.7634. Min Range: -0.7634

Max Act: 0.5118. Min Act: -0.0000

Data Index: 1567231 (Python Code)

Max Activating Token Index: 773

Text #16

Max Range: 0.7634. Min Range: -0.7634

Max Act: 0.5885. Min Act: -0.0000

Data Index: 1654011 (Python Code)

Max Activating Token Index: 540

Text #17

Max Range: 0.7634. Min Range: -0.7634

Max Act: 0.5313. Min Act: -0.0000

Data Index: 1586472 (Python Code)

Max Activating Token Index: 941

Text #18

Max Range: 0.7634. Min Range: -0.7634

Max Act: 0.5422. Min Act: -0.0000

Data Index: 1536116 (Python Code)

Max Activating Token Index: 998

Text #19

Max Range: 0.7634. Min Range: -0.7634

Max Act: 0.5376. Min Act: -0.0000

Data Index: 1615567 (Python Code)

Max Activating Token Index: 695