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

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

Neuron 4243 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: 2.8741. Min Range: -2.8741

Max Act: 2.8741. Min Act: -0.0000

Data Index: 1165400 (C4 (Web Text))

Max Activating Token Index: 841

Text #1

Max Range: 2.8741. Min Range: -2.8741

Max Act: 1.7925. Min Act: -0.0000

Data Index: 46780 (C4 (Web Text))

Max Activating Token Index: 695

Text #2

Max Range: 2.8741. Min Range: -2.8741

Max Act: 2.2624. Min Act: -0.0000

Data Index: 614513 (C4 (Web Text))

Max Activating Token Index: 515

Text #3

Max Range: 2.8741. Min Range: -2.8741

Max Act: 2.0458. Min Act: -0.0000

Data Index: 425427 (C4 (Web Text))

Max Activating Token Index: 788

Text #4

Max Range: 2.8741. Min Range: -2.8741

Max Act: 2.0670. Min Act: -0.0000

Data Index: 348880 (C4 (Web Text))

Max Activating Token Index: 416

Text #5

Max Range: 2.8741. Min Range: -2.8741

Max Act: 2.0581. Min Act: -0.0000

Data Index: 918673 (C4 (Web Text))

Max Activating Token Index: 285

Text #6

Max Range: 2.8741. Min Range: -2.8741

Max Act: 2.1456. Min Act: -0.0000

Data Index: 1340314 (C4 (Web Text))

Max Activating Token Index: 660

Text #7

Max Range: 2.8741. Min Range: -2.8741

Max Act: 1.8487. Min Act: -0.0000

Data Index: 97892 (C4 (Web Text))

Max Activating Token Index: 250

Text #8

Max Range: 2.8741. Min Range: -2.8741

Max Act: 1.9506. Min Act: -0.0000

Data Index: 1067866 (C4 (Web Text))

Max Activating Token Index: 506

Text #9

Max Range: 2.8741. Min Range: -2.8741

Max Act: 1.7080. Min Act: -0.0000

Data Index: 1203281 (C4 (Web Text))

Max Activating Token Index: 679

Text #10

Max Range: 2.8741. Min Range: -2.8741

Max Act: 1.5471. Min Act: -0.0000

Data Index: 1004528 (C4 (Web Text))

Max Activating Token Index: 263

Text #11

Max Range: 2.8741. Min Range: -2.8741

Max Act: 1.6324. Min Act: -0.0000

Data Index: 1206991 (C4 (Web Text))

Max Activating Token Index: 866

Text #12

Max Range: 2.8741. Min Range: -2.8741

Max Act: 1.7057. Min Act: -0.0000

Data Index: 91855 (C4 (Web Text))

Max Activating Token Index: 627

Text #13

Max Range: 2.8741. Min Range: -2.8741

Max Act: 1.5494. Min Act: -0.0000

Data Index: 1106409 (C4 (Web Text))

Max Activating Token Index: 1018

Text #14

Max Range: 2.8741. Min Range: -2.8741

Max Act: 1.6401. Min Act: -0.0000

Data Index: 1312125 (C4 (Web Text))

Max Activating Token Index: 575

Text #15

Max Range: 2.8741. Min Range: -2.8741

Max Act: 1.5021. Min Act: -0.0000

Data Index: 1196898 (C4 (Web Text))

Max Activating Token Index: 678

Text #16

Max Range: 2.8741. Min Range: -2.8741

Max Act: 1.6669. Min Act: -0.0000

Data Index: 425194 (C4 (Web Text))

Max Activating Token Index: 550

Text #17

Max Range: 2.8741. Min Range: -2.8741

Max Act: 1.4989. Min Act: -0.0000

Data Index: 920736 (C4 (Web Text))

Max Activating Token Index: 767

Text #18

Max Range: 2.8741. Min Range: -2.8741

Max Act: 1.4962. Min Act: -0.0000

Data Index: 634513 (C4 (Web Text))

Max Activating Token Index: 434

Text #19

Max Range: 2.8741. Min Range: -2.8741

Max Act: 1.5969. Min Act: -0.0000

Data Index: 885520 (C4 (Web Text))

Max Activating Token Index: 409