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

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

Neuron 2125 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2528. Min Range: -1.2528

Max Act: 1.2528. Min Act: -0.0000

Data Index: 596218 (C4 (Web Text))

Max Activating Token Index: 638

Text #1

Max Range: 1.2528. Min Range: -1.2528

Max Act: 1.2085. Min Act: -0.0000

Data Index: 1096758 (C4 (Web Text))

Max Activating Token Index: 917

Text #2

Max Range: 1.2528. Min Range: -1.2528

Max Act: 1.0850. Min Act: -0.0000

Data Index: 783785 (C4 (Web Text))

Max Activating Token Index: 526

Text #3

Max Range: 1.2528. Min Range: -1.2528

Max Act: 0.9727. Min Act: -0.0000

Data Index: 1125163 (C4 (Web Text))

Max Activating Token Index: 253

Text #4

Max Range: 1.2528. Min Range: -1.2528

Max Act: 0.7189. Min Act: -0.0000

Data Index: 1113166 (C4 (Web Text))

Max Activating Token Index: 895

Text #5

Max Range: 1.2528. Min Range: -1.2528

Max Act: 0.7049. Min Act: -0.0000

Data Index: 639658 (C4 (Web Text))

Max Activating Token Index: 750

Text #6

Max Range: 1.2528. Min Range: -1.2528

Max Act: 0.6887. Min Act: -0.0000

Data Index: 796131 (C4 (Web Text))

Max Activating Token Index: 878

Text #7

Max Range: 1.2528. Min Range: -1.2528

Max Act: 0.6908. Min Act: -0.0000

Data Index: 1266373 (C4 (Web Text))

Max Activating Token Index: 966

Text #8

Max Range: 1.2528. Min Range: -1.2528

Max Act: 0.6626. Min Act: -0.0000

Data Index: 785836 (C4 (Web Text))

Max Activating Token Index: 936

Text #9

Max Range: 1.2528. Min Range: -1.2528

Max Act: 0.6618. Min Act: -0.0000

Data Index: 1035600 (C4 (Web Text))

Max Activating Token Index: 457

Text #10

Max Range: 1.2528. Min Range: -1.2528

Max Act: 0.6418. Min Act: -0.0000

Data Index: 1062949 (C4 (Web Text))

Max Activating Token Index: 416

Text #11

Max Range: 1.2528. Min Range: -1.2528

Max Act: 0.6408. Min Act: -0.0000

Data Index: 1148738 (C4 (Web Text))

Max Activating Token Index: 660

Text #12

Max Range: 1.2528. Min Range: -1.2528

Max Act: 0.6782. Min Act: -0.0000

Data Index: 990103 (C4 (Web Text))

Max Activating Token Index: 739

Text #13

Max Range: 1.2528. Min Range: -1.2528

Max Act: 0.6475. Min Act: -0.0000

Data Index: 744451 (C4 (Web Text))

Max Activating Token Index: 838

Text #14

Max Range: 1.2528. Min Range: -1.2528

Max Act: 0.6708. Min Act: -0.0000

Data Index: 1163426 (C4 (Web Text))

Max Activating Token Index: 1011

Text #15

Max Range: 1.2528. Min Range: -1.2528

Max Act: 0.6645. Min Act: -0.0000

Data Index: 1350932 (C4 (Web Text))

Max Activating Token Index: 777

Text #16

Max Range: 1.2528. Min Range: -1.2528

Max Act: 0.6405. Min Act: -0.0000

Data Index: 841244 (C4 (Web Text))

Max Activating Token Index: 728

Text #17

Max Range: 1.2528. Min Range: -1.2528

Max Act: 0.6566. Min Act: -0.0000

Data Index: 1288356 (C4 (Web Text))

Max Activating Token Index: 806

Text #18

Max Range: 1.2528. Min Range: -1.2528

Max Act: 0.6336. Min Act: -0.0000

Data Index: 584322 (C4 (Web Text))

Max Activating Token Index: 920

Text #19

Max Range: 1.2528. Min Range: -1.2528

Max Act: 0.6270. Min Act: -0.0000

Data Index: 631742 (C4 (Web Text))

Max Activating Token Index: 863