Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 369 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.8460. Min Range: -1.8460

Max Act: 1.8460. Min Act: -0.0000

Data Index: 914577 (C4 (Web Text))

Max Activating Token Index: 370

Text #1

Max Range: 1.8460. Min Range: -1.8460

Max Act: 1.7216. Min Act: -0.0000

Data Index: 1274314 (C4 (Web Text))

Max Activating Token Index: 931

Text #2

Max Range: 1.8460. Min Range: -1.8460

Max Act: 1.7164. Min Act: -0.0000

Data Index: 1208322 (C4 (Web Text))

Max Activating Token Index: 92

Text #3

Max Range: 1.8460. Min Range: -1.8460

Max Act: 1.5486. Min Act: -0.0000

Data Index: 1084211 (C4 (Web Text))

Max Activating Token Index: 940

Text #4

Max Range: 1.8460. Min Range: -1.8460

Max Act: 1.6186. Min Act: -0.0000

Data Index: 225571 (C4 (Web Text))

Max Activating Token Index: 869

Text #5

Max Range: 1.8460. Min Range: -1.8460

Max Act: 1.6029. Min Act: -0.0000

Data Index: 1141014 (C4 (Web Text))

Max Activating Token Index: 124

Text #6

Max Range: 1.8460. Min Range: -1.8460

Max Act: 1.5538. Min Act: -0.0000

Data Index: 743236 (C4 (Web Text))

Max Activating Token Index: 419

Text #7

Max Range: 1.8460. Min Range: -1.8460

Max Act: 1.5049. Min Act: -0.0000

Data Index: 834572 (C4 (Web Text))

Max Activating Token Index: 824

Text #8

Max Range: 1.8460. Min Range: -1.8460

Max Act: 1.4100. Min Act: -0.0000

Data Index: 508321 (C4 (Web Text))

Max Activating Token Index: 681

Text #9

Max Range: 1.8460. Min Range: -1.8460

Max Act: 1.4016. Min Act: -0.0000

Data Index: 569938 (C4 (Web Text))

Max Activating Token Index: 362

Text #10

Max Range: 1.8460. Min Range: -1.8460

Max Act: 1.4741. Min Act: -0.0000

Data Index: 672696 (C4 (Web Text))

Max Activating Token Index: 749

Text #11

Max Range: 1.8460. Min Range: -1.8460

Max Act: 1.4504. Min Act: -0.0000

Data Index: 130282 (C4 (Web Text))

Max Activating Token Index: 803

Text #12

Max Range: 1.8460. Min Range: -1.8460

Max Act: 1.5228. Min Act: -0.0000

Data Index: 67190 (C4 (Web Text))

Max Activating Token Index: 164

Text #13

Max Range: 1.8460. Min Range: -1.8460

Max Act: 1.2798. Min Act: -0.0000

Data Index: 88173 (C4 (Web Text))

Max Activating Token Index: 415

Text #14

Max Range: 1.8460. Min Range: -1.8460

Max Act: 1.3756. Min Act: -0.0000

Data Index: 799531 (C4 (Web Text))

Max Activating Token Index: 180

Text #15

Max Range: 1.8460. Min Range: -1.8460

Max Act: 1.3834. Min Act: -0.0000

Data Index: 347060 (C4 (Web Text))

Max Activating Token Index: 228

Text #16

Max Range: 1.8460. Min Range: -1.8460

Max Act: 1.3889. Min Act: -0.0000

Data Index: 750887 (C4 (Web Text))

Max Activating Token Index: 673

Text #17

Max Range: 1.8460. Min Range: -1.8460

Max Act: 1.3036. Min Act: -0.0000

Data Index: 539474 (C4 (Web Text))

Max Activating Token Index: 992

Text #18

Max Range: 1.8460. Min Range: -1.8460

Max Act: 1.2755. Min Act: -0.0000

Data Index: 1323634 (C4 (Web Text))

Max Activating Token Index: 905

Text #19

Max Range: 1.8460. Min Range: -1.8460

Max Act: 1.2044. Min Act: -0.0000

Data Index: 177045 (C4 (Web Text))

Max Activating Token Index: 758