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

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

Neuron 129 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: 1.4627. Min Range: -1.4627

Max Act: 1.4627. Min Act: -0.0001

Data Index: 94018 (C4 (Web Text))

Max Activating Token Index: 935

Text #1

Max Range: 1.4627. Min Range: -1.4627

Max Act: 1.3443. Min Act: -0.0001

Data Index: 89842 (C4 (Web Text))

Max Activating Token Index: 585

Text #2

Max Range: 1.4627. Min Range: -1.4627

Max Act: 1.4082. Min Act: -0.0001

Data Index: 621800 (C4 (Web Text))

Max Activating Token Index: 593

Text #3

Max Range: 1.4627. Min Range: -1.4627

Max Act: 1.3223. Min Act: -0.0001

Data Index: 884261 (C4 (Web Text))

Max Activating Token Index: 679

Text #4

Max Range: 1.4627. Min Range: -1.4627

Max Act: 1.2803. Min Act: -0.0001

Data Index: 697272 (C4 (Web Text))

Max Activating Token Index: 967

Text #5

Max Range: 1.4627. Min Range: -1.4627

Max Act: 1.1126. Min Act: -0.0001

Data Index: 588940 (C4 (Web Text))

Max Activating Token Index: 895

Text #6

Max Range: 1.4627. Min Range: -1.4627

Max Act: 1.1696. Min Act: -0.0001

Data Index: 76856 (C4 (Web Text))

Max Activating Token Index: 434

Text #7

Max Range: 1.4627. Min Range: -1.4627

Max Act: 1.1270. Min Act: -0.0001

Data Index: 1053706 (C4 (Web Text))

Max Activating Token Index: 307

Text #8

Max Range: 1.4627. Min Range: -1.4627

Max Act: 1.1581. Min Act: -0.0001

Data Index: 948286 (C4 (Web Text))

Max Activating Token Index: 314

Text #9

Max Range: 1.4627. Min Range: -1.4627

Max Act: 1.1798. Min Act: -0.0001

Data Index: 577665 (C4 (Web Text))

Max Activating Token Index: 882

Text #10

Max Range: 1.4627. Min Range: -1.4627

Max Act: 0.9979. Min Act: -0.0001

Data Index: 280394 (C4 (Web Text))

Max Activating Token Index: 345

Text #11

Max Range: 1.4627. Min Range: -1.4627

Max Act: 1.1657. Min Act: -0.0001

Data Index: 1029954 (C4 (Web Text))

Max Activating Token Index: 593

Text #12

Max Range: 1.4627. Min Range: -1.4627

Max Act: 1.2250. Min Act: -0.0001

Data Index: 1059189 (C4 (Web Text))

Max Activating Token Index: 234

Text #13

Max Range: 1.4627. Min Range: -1.4627

Max Act: 1.1098. Min Act: -0.0001

Data Index: 908482 (C4 (Web Text))

Max Activating Token Index: 25

Text #14

Max Range: 1.4627. Min Range: -1.4627

Max Act: 1.0567. Min Act: -0.0001

Data Index: 165591 (C4 (Web Text))

Max Activating Token Index: 146

Text #15

Max Range: 1.4627. Min Range: -1.4627

Max Act: 1.0233. Min Act: -0.0001

Data Index: 604671 (C4 (Web Text))

Max Activating Token Index: 400

Text #16

Max Range: 1.4627. Min Range: -1.4627

Max Act: 1.0033. Min Act: -0.0001

Data Index: 1253698 (C4 (Web Text))

Max Activating Token Index: 123

Text #17

Max Range: 1.4627. Min Range: -1.4627

Max Act: 1.0905. Min Act: -0.0001

Data Index: 887577 (C4 (Web Text))

Max Activating Token Index: 261

Text #18

Max Range: 1.4627. Min Range: -1.4627

Max Act: 0.9569. Min Act: -0.0001

Data Index: 602455 (C4 (Web Text))

Max Activating Token Index: 648

Text #19

Max Range: 1.4627. Min Range: -1.4627

Max Act: 1.0033. Min Act: -0.0001

Data Index: 1184490 (C4 (Web Text))

Max Activating Token Index: 431