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

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

Neuron 4105 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9477. Min Range: -0.9477

Max Act: 0.9007. Min Act: -0.0000

Data Index: 1486983 (Python Code)

Max Activating Token Index: 930

Text #1

Max Range: 0.9477. Min Range: -0.9477

Max Act: 0.9477. Min Act: -0.0000

Data Index: 1532434 (Python Code)

Max Activating Token Index: 375

Text #2

Max Range: 0.9477. Min Range: -0.9477

Max Act: 0.7812. Min Act: -0.0000

Data Index: 1516677 (Python Code)

Max Activating Token Index: 284

Text #3

Max Range: 0.9477. Min Range: -0.9477

Max Act: 0.7708. Min Act: -0.0000

Data Index: 1414989 (Python Code)

Max Activating Token Index: 913

Text #4

Max Range: 0.9477. Min Range: -0.9477

Max Act: 0.6574. Min Act: -0.0000

Data Index: 1479770 (Python Code)

Max Activating Token Index: 281

Text #5

Max Range: 0.9477. Min Range: -0.9477

Max Act: 0.7790. Min Act: -0.0000

Data Index: 1549007 (Python Code)

Max Activating Token Index: 600

Text #6

Max Range: 0.9477. Min Range: -0.9477

Max Act: 0.8745. Min Act: -0.0000

Data Index: 1444038 (Python Code)

Max Activating Token Index: 109

Text #7

Max Range: 0.9477. Min Range: -0.9477

Max Act: 0.8323. Min Act: -0.0000

Data Index: 1464057 (Python Code)

Max Activating Token Index: 448

Text #8

Max Range: 0.9477. Min Range: -0.9477

Max Act: 0.7163. Min Act: -0.0000

Data Index: 1415227 (Python Code)

Max Activating Token Index: 137

Text #9

Max Range: 0.9477. Min Range: -0.9477

Max Act: 0.8500. Min Act: -0.0000

Data Index: 1637563 (Python Code)

Max Activating Token Index: 221

Text #10

Max Range: 0.9477. Min Range: -0.9477

Max Act: 0.7618. Min Act: -0.0000

Data Index: 1443526 (Python Code)

Max Activating Token Index: 206

Text #11

Max Range: 0.9477. Min Range: -0.9477

Max Act: 0.7408. Min Act: -0.0000

Data Index: 1559701 (Python Code)

Max Activating Token Index: 593

Text #12

Max Range: 0.9477. Min Range: -0.9477

Max Act: 0.6370. Min Act: -0.0000

Data Index: 1442911 (Python Code)

Max Activating Token Index: 587

Text #13

Max Range: 0.9477. Min Range: -0.9477

Max Act: 0.7292. Min Act: -0.0000

Data Index: 1597616 (Python Code)

Max Activating Token Index: 908

Text #14

Max Range: 0.9477. Min Range: -0.9477

Max Act: 0.6801. Min Act: -0.0000

Data Index: 1482592 (Python Code)

Max Activating Token Index: 695

Text #15

Max Range: 0.9477. Min Range: -0.9477

Max Act: 0.6688. Min Act: -0.0000

Data Index: 1569925 (Python Code)

Max Activating Token Index: 231

Text #16

Max Range: 0.9477. Min Range: -0.9477

Max Act: 0.7262. Min Act: -0.0000

Data Index: 1389166 (Python Code)

Max Activating Token Index: 616

Text #17

Max Range: 0.9477. Min Range: -0.9477

Max Act: 0.7725. Min Act: -0.0001

Data Index: 1400088 (Python Code)

Max Activating Token Index: 105

Text #18

Max Range: 0.9477. Min Range: -0.9477

Max Act: 0.6808. Min Act: -0.0000

Data Index: 1481349 (Python Code)

Max Activating Token Index: 871

Text #19

Max Range: 0.9477. Min Range: -0.9477

Max Act: 0.7671. Min Act: -0.0000

Data Index: 1639492 (Python Code)

Max Activating Token Index: 221