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

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

Neuron 590 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0255. Min Range: -3.0255

Max Act: 2.8591. Min Act: -0.0000

Data Index: 1398779 (Python Code)

Max Activating Token Index: 941

Text #1

Max Range: 3.0255. Min Range: -3.0255

Max Act: 3.0255. Min Act: -0.0000

Data Index: 1492773 (Python Code)

Max Activating Token Index: 871

Text #2

Max Range: 3.0255. Min Range: -3.0255

Max Act: 2.6137. Min Act: -0.0000

Data Index: 1392738 (Python Code)

Max Activating Token Index: 232

Text #3

Max Range: 3.0255. Min Range: -3.0255

Max Act: 2.7877. Min Act: -0.0000

Data Index: 1365611 (Python Code)

Max Activating Token Index: 965

Text #4

Max Range: 3.0255. Min Range: -3.0255

Max Act: 2.4948. Min Act: -0.0000

Data Index: 1405657 (Python Code)

Max Activating Token Index: 761

Text #5

Max Range: 3.0255. Min Range: -3.0255

Max Act: 2.4209. Min Act: -0.0000

Data Index: 1374729 (Python Code)

Max Activating Token Index: 847

Text #6

Max Range: 3.0255. Min Range: -3.0255

Max Act: 2.5858. Min Act: -0.0000

Data Index: 1535587 (Python Code)

Max Activating Token Index: 416

Text #7

Max Range: 3.0255. Min Range: -3.0255

Max Act: 2.3020. Min Act: -0.0000

Data Index: 1569559 (Python Code)

Max Activating Token Index: 294

Text #8

Max Range: 3.0255. Min Range: -3.0255

Max Act: 2.6490. Min Act: -0.0000

Data Index: 1560700 (Python Code)

Max Activating Token Index: 699

Text #9

Max Range: 3.0255. Min Range: -3.0255

Max Act: 2.6259. Min Act: -0.0000

Data Index: 1478656 (Python Code)

Max Activating Token Index: 241

Text #10

Max Range: 3.0255. Min Range: -3.0255

Max Act: 2.3897. Min Act: -0.0000

Data Index: 1516747 (Python Code)

Max Activating Token Index: 577

Text #11

Max Range: 3.0255. Min Range: -3.0255

Max Act: 2.4747. Min Act: -0.0000

Data Index: 1625086 (Python Code)

Max Activating Token Index: 917

Text #12

Max Range: 3.0255. Min Range: -3.0255

Max Act: 2.3497. Min Act: -0.0000

Data Index: 1651510 (Python Code)

Max Activating Token Index: 868

Text #13

Max Range: 3.0255. Min Range: -3.0255

Max Act: 2.3084. Min Act: -0.0000

Data Index: 1447688 (Python Code)

Max Activating Token Index: 336

Text #14

Max Range: 3.0255. Min Range: -3.0255

Max Act: 2.4003. Min Act: -0.0000

Data Index: 1437842 (Python Code)

Max Activating Token Index: 595

Text #15

Max Range: 3.0255. Min Range: -3.0255

Max Act: 2.3698. Min Act: -0.0000

Data Index: 1535253 (Python Code)

Max Activating Token Index: 953

Text #16

Max Range: 3.0255. Min Range: -3.0255

Max Act: 2.2211. Min Act: -0.0000

Data Index: 1374867 (Python Code)

Max Activating Token Index: 719

Text #17

Max Range: 3.0255. Min Range: -3.0255

Max Act: 2.0978. Min Act: -0.0000

Data Index: 1451224 (Python Code)

Max Activating Token Index: 653

Text #18

Max Range: 3.0255. Min Range: -3.0255

Max Act: 2.3172. Min Act: -0.0000

Data Index: 1361152 (Python Code)

Max Activating Token Index: 710

Text #19

Max Range: 3.0255. Min Range: -3.0255

Max Act: 2.1982. Min Act: -0.0000

Data Index: 1506022 (Python Code)

Max Activating Token Index: 208