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

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

Neuron 3642 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: 0.1138. Min Range: -0.1138

Max Act: 0.1138. Min Act: -0.0001

Data Index: 157658 (C4 (Web Text))

Max Activating Token Index: 303

Text #1

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.1120. Min Act: -0.0001

Data Index: 1347111 (C4 (Web Text))

Max Activating Token Index: 321

Text #2

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.0811. Min Act: -0.0001

Data Index: 1158811 (C4 (Web Text))

Max Activating Token Index: 998

Text #3

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.0928. Min Act: -0.0001

Data Index: 340090 (C4 (Web Text))

Max Activating Token Index: 885

Text #4

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.0745. Min Act: -0.0001

Data Index: 208507 (C4 (Web Text))

Max Activating Token Index: 825

Text #5

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.0844. Min Act: -0.0001

Data Index: 400108 (C4 (Web Text))

Max Activating Token Index: 641

Text #6

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.0755. Min Act: -0.0001

Data Index: 1280390 (C4 (Web Text))

Max Activating Token Index: 150

Text #7

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.0703. Min Act: -0.0001

Data Index: 1118764 (C4 (Web Text))

Max Activating Token Index: 442

Text #8

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.0756. Min Act: -0.0001

Data Index: 441134 (C4 (Web Text))

Max Activating Token Index: 318

Text #9

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.0746. Min Act: -0.0001

Data Index: 144675 (C4 (Web Text))

Max Activating Token Index: 581

Text #10

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.0677. Min Act: -0.0001

Data Index: 947420 (C4 (Web Text))

Max Activating Token Index: 523

Text #11

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.0705. Min Act: -0.0001

Data Index: 545715 (C4 (Web Text))

Max Activating Token Index: 747

Text #12

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.0651. Min Act: -0.0000

Data Index: 1059957 (C4 (Web Text))

Max Activating Token Index: 685

Text #13

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.0692. Min Act: -0.0001

Data Index: 1149609 (C4 (Web Text))

Max Activating Token Index: 833

Text #14

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.0653. Min Act: -0.0001

Data Index: 1021315 (C4 (Web Text))

Max Activating Token Index: 111

Text #15

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.0605. Min Act: -0.0001

Data Index: 188812 (C4 (Web Text))

Max Activating Token Index: 781

Text #16

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.0623. Min Act: -0.0000

Data Index: 274100 (C4 (Web Text))

Max Activating Token Index: 33

Text #17

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.0668. Min Act: -0.0000

Data Index: 371795 (C4 (Web Text))

Max Activating Token Index: 564

Text #18

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.0657. Min Act: -0.0001

Data Index: 184887 (C4 (Web Text))

Max Activating Token Index: 616

Text #19

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.0614. Min Act: -0.0001

Data Index: 580490 (C4 (Web Text))

Max Activating Token Index: 975