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

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

Neuron 4825 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 2.9115. Min Range: -2.9115

Max Act: 2.9115. Min Act: -0.0002

Data Index: 1303113 (C4 (Web Text))

Max Activating Token Index: 573

Text #1

Max Range: 2.9115. Min Range: -2.9115

Max Act: 2.4700. Min Act: -0.0002

Data Index: 686719 (C4 (Web Text))

Max Activating Token Index: 747

Text #2

Max Range: 2.9115. Min Range: -2.9115

Max Act: 2.5133. Min Act: -0.0002

Data Index: 1274348 (C4 (Web Text))

Max Activating Token Index: 803

Text #3

Max Range: 2.9115. Min Range: -2.9115

Max Act: 2.4672. Min Act: -0.0002

Data Index: 634566 (C4 (Web Text))

Max Activating Token Index: 695

Text #4

Max Range: 2.9115. Min Range: -2.9115

Max Act: 2.4579. Min Act: -0.0002

Data Index: 34407 (C4 (Web Text))

Max Activating Token Index: 813

Text #5

Max Range: 2.9115. Min Range: -2.9115

Max Act: 2.5710. Min Act: -0.0002

Data Index: 341861 (C4 (Web Text))

Max Activating Token Index: 756

Text #6

Max Range: 2.9115. Min Range: -2.9115

Max Act: 2.4371. Min Act: -0.0002

Data Index: 535910 (C4 (Web Text))

Max Activating Token Index: 924

Text #7

Max Range: 2.9115. Min Range: -2.9115

Max Act: 2.4046. Min Act: -0.0002

Data Index: 583400 (C4 (Web Text))

Max Activating Token Index: 780

Text #8

Max Range: 2.9115. Min Range: -2.9115

Max Act: 2.3725. Min Act: -0.0002

Data Index: 1302921 (C4 (Web Text))

Max Activating Token Index: 832

Text #9

Max Range: 2.9115. Min Range: -2.9115

Max Act: 2.3878. Min Act: -0.0002

Data Index: 922669 (C4 (Web Text))

Max Activating Token Index: 1000

Text #10

Max Range: 2.9115. Min Range: -2.9115

Max Act: 2.3975. Min Act: -0.0002

Data Index: 43342 (C4 (Web Text))

Max Activating Token Index: 706

Text #11

Max Range: 2.9115. Min Range: -2.9115

Max Act: 2.3992. Min Act: -0.0003

Data Index: 728315 (C4 (Web Text))

Max Activating Token Index: 836

Text #12

Max Range: 2.9115. Min Range: -2.9115

Max Act: 2.3508. Min Act: -0.0002

Data Index: 1022805 (C4 (Web Text))

Max Activating Token Index: 700

Text #13

Max Range: 2.9115. Min Range: -2.9115

Max Act: 2.4181. Min Act: -0.0002

Data Index: 236253 (C4 (Web Text))

Max Activating Token Index: 697

Text #14

Max Range: 2.9115. Min Range: -2.9115

Max Act: 2.4263. Min Act: -0.0002

Data Index: 83619 (C4 (Web Text))

Max Activating Token Index: 74

Text #15

Max Range: 2.9115. Min Range: -2.9115

Max Act: 2.3496. Min Act: -0.0002

Data Index: 1179242 (C4 (Web Text))

Max Activating Token Index: 740

Text #16

Max Range: 2.9115. Min Range: -2.9115

Max Act: 2.3667. Min Act: -0.0002

Data Index: 1266893 (C4 (Web Text))

Max Activating Token Index: 845

Text #17

Max Range: 2.9115. Min Range: -2.9115

Max Act: 2.3361. Min Act: -0.0002

Data Index: 1025895 (C4 (Web Text))

Max Activating Token Index: 793

Text #18

Max Range: 2.9115. Min Range: -2.9115

Max Act: 2.3416. Min Act: -0.0002

Data Index: 436197 (C4 (Web Text))

Max Activating Token Index: 885

Text #19

Max Range: 2.9115. Min Range: -2.9115

Max Act: 2.3263. Min Act: -0.0002

Data Index: 1027253 (C4 (Web Text))

Max Activating Token Index: 107