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

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

Neuron 3720 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0958. Min Act: -0.0002

Data Index: 941594 (C4 (Web Text))

Max Activating Token Index: 493

Text #1

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0930. Min Act: -0.0002

Data Index: 275027 (C4 (Web Text))

Max Activating Token Index: 436

Text #2

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0882. Min Act: -0.0002

Data Index: 1112922 (C4 (Web Text))

Max Activating Token Index: 607

Text #3

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0883. Min Act: -0.0002

Data Index: 523874 (C4 (Web Text))

Max Activating Token Index: 222

Text #4

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0838. Min Act: -0.0002

Data Index: 507349 (C4 (Web Text))

Max Activating Token Index: 490

Text #5

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0838. Min Act: -0.0002

Data Index: 926581 (C4 (Web Text))

Max Activating Token Index: 219

Text #6

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0828. Min Act: -0.0002

Data Index: 631523 (C4 (Web Text))

Max Activating Token Index: 998

Text #7

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0825. Min Act: -0.0002

Data Index: 1132234 (C4 (Web Text))

Max Activating Token Index: 21

Text #8

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0807. Min Act: -0.0002

Data Index: 744280 (C4 (Web Text))

Max Activating Token Index: 269

Text #9

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0788. Min Act: -0.0002

Data Index: 266462 (C4 (Web Text))

Max Activating Token Index: 997

Text #10

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0767. Min Act: -0.0002

Data Index: 1275691 (C4 (Web Text))

Max Activating Token Index: 353

Text #11

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0759. Min Act: -0.0002

Data Index: 188654 (C4 (Web Text))

Max Activating Token Index: 715

Text #12

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0758. Min Act: -0.0002

Data Index: 1309781 (C4 (Web Text))

Max Activating Token Index: 120

Text #13

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0756. Min Act: -0.0002

Data Index: 248142 (C4 (Web Text))

Max Activating Token Index: 440

Text #14

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0753. Min Act: -0.0002

Data Index: 168688 (C4 (Web Text))

Max Activating Token Index: 115

Text #15

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0751. Min Act: -0.0002

Data Index: 769588 (C4 (Web Text))

Max Activating Token Index: 641

Text #16

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0747. Min Act: -0.0002

Data Index: 785192 (C4 (Web Text))

Max Activating Token Index: 72

Text #17

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0726. Min Act: -0.0002

Data Index: 961815 (C4 (Web Text))

Max Activating Token Index: 772

Text #18

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0741. Min Act: -0.0002

Data Index: 240529 (C4 (Web Text))

Max Activating Token Index: 946

Text #19

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0729. Min Act: -0.0002

Data Index: 173611 (C4 (Web Text))

Max Activating Token Index: 888