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

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

Neuron 2512 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6133. Min Range: -0.6133

Max Act: 0.6133. Min Act: -0.0002

Data Index: 1518988 (Python Code)

Max Activating Token Index: 198

Text #1

Max Range: 0.6133. Min Range: -0.6133

Max Act: 0.6032. Min Act: -0.0002

Data Index: 1441313 (Python Code)

Max Activating Token Index: 224

Text #2

Max Range: 0.6133. Min Range: -0.6133

Max Act: 0.5441. Min Act: -0.0002

Data Index: 1476009 (Python Code)

Max Activating Token Index: 255

Text #3

Max Range: 0.6133. Min Range: -0.6133

Max Act: 0.5732. Min Act: -0.0002

Data Index: 1451274 (Python Code)

Max Activating Token Index: 608

Text #4

Max Range: 0.6133. Min Range: -0.6133

Max Act: 0.5400. Min Act: -0.0002

Data Index: 1398090 (Python Code)

Max Activating Token Index: 937

Text #5

Max Range: 0.6133. Min Range: -0.6133

Max Act: 0.5350. Min Act: -0.0002

Data Index: 1468517 (Python Code)

Max Activating Token Index: 415

Text #6

Max Range: 0.6133. Min Range: -0.6133

Max Act: 0.5278. Min Act: -0.0002

Data Index: 1496478 (Python Code)

Max Activating Token Index: 649

Text #7

Max Range: 0.6133. Min Range: -0.6133

Max Act: 0.5020. Min Act: -0.0002

Data Index: 1584832 (Python Code)

Max Activating Token Index: 906

Text #8

Max Range: 0.6133. Min Range: -0.6133

Max Act: 0.5307. Min Act: -0.0002

Data Index: 1485224 (Python Code)

Max Activating Token Index: 999

Text #9

Max Range: 0.6133. Min Range: -0.6133

Max Act: 0.5043. Min Act: -0.0002

Data Index: 1573182 (Python Code)

Max Activating Token Index: 615

Text #10

Max Range: 0.6133. Min Range: -0.6133

Max Act: 0.5062. Min Act: -0.0002

Data Index: 1587895 (Python Code)

Max Activating Token Index: 10

Text #11

Max Range: 0.6133. Min Range: -0.6133

Max Act: 0.5011. Min Act: -0.0002

Data Index: 1537979 (Python Code)

Max Activating Token Index: 481

Text #12

Max Range: 0.6133. Min Range: -0.6133

Max Act: 0.4983. Min Act: -0.0002

Data Index: 1360698 (Python Code)

Max Activating Token Index: 403

Text #13

Max Range: 0.6133. Min Range: -0.6133

Max Act: 0.4970. Min Act: -0.0002

Data Index: 1592646 (Python Code)

Max Activating Token Index: 240

Text #14

Max Range: 0.6133. Min Range: -0.6133

Max Act: 0.5109. Min Act: -0.0002

Data Index: 1449140 (Python Code)

Max Activating Token Index: 55

Text #15

Max Range: 0.6133. Min Range: -0.6133

Max Act: 0.4727. Min Act: -0.0002

Data Index: 1630153 (Python Code)

Max Activating Token Index: 695

Text #16

Max Range: 0.6133. Min Range: -0.6133

Max Act: 0.5072. Min Act: -0.0002

Data Index: 1375843 (Python Code)

Max Activating Token Index: 846

Text #17

Max Range: 0.6133. Min Range: -0.6133

Max Act: 0.4778. Min Act: -0.0002

Data Index: 1579653 (Python Code)

Max Activating Token Index: 709

Text #18

Max Range: 0.6133. Min Range: -0.6133

Max Act: 0.4917. Min Act: -0.0002

Data Index: 1427195 (Python Code)

Max Activating Token Index: 961

Text #19

Max Range: 0.6133. Min Range: -0.6133

Max Act: 0.4764. Min Act: -0.0002

Data Index: 1531309 (Python Code)

Max Activating Token Index: 494