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

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

Neuron 3796 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7737. Min Range: -0.7737

Max Act: 0.7737. Min Act: -0.0003

Data Index: 1074887 (C4 (Web Text))

Max Activating Token Index: 325

Text #1

Max Range: 0.7737. Min Range: -0.7737

Max Act: 0.6731. Min Act: -0.0003

Data Index: 1047465 (C4 (Web Text))

Max Activating Token Index: 834

Text #2

Max Range: 0.7737. Min Range: -0.7737

Max Act: 0.6525. Min Act: -0.0002

Data Index: 972441 (C4 (Web Text))

Max Activating Token Index: 210

Text #3

Max Range: 0.7737. Min Range: -0.7737

Max Act: 0.6482. Min Act: -0.0002

Data Index: 873346 (C4 (Web Text))

Max Activating Token Index: 816

Text #4

Max Range: 0.7737. Min Range: -0.7737

Max Act: 0.5878. Min Act: -0.0003

Data Index: 1247498 (C4 (Web Text))

Max Activating Token Index: 35

Text #5

Max Range: 0.7737. Min Range: -0.7737

Max Act: 0.6226. Min Act: -0.0002

Data Index: 344954 (C4 (Web Text))

Max Activating Token Index: 599

Text #6

Max Range: 0.7737. Min Range: -0.7737

Max Act: 0.5970. Min Act: -0.0003

Data Index: 682491 (C4 (Web Text))

Max Activating Token Index: 731

Text #7

Max Range: 0.7737. Min Range: -0.7737

Max Act: 0.6154. Min Act: -0.0003

Data Index: 975250 (C4 (Web Text))

Max Activating Token Index: 246

Text #8

Max Range: 0.7737. Min Range: -0.7737

Max Act: 0.5926. Min Act: -0.0003

Data Index: 1031953 (C4 (Web Text))

Max Activating Token Index: 549

Text #9

Max Range: 0.7737. Min Range: -0.7737

Max Act: 0.5909. Min Act: -0.0003

Data Index: 640881 (C4 (Web Text))

Max Activating Token Index: 170

Text #10

Max Range: 0.7737. Min Range: -0.7737

Max Act: 0.5890. Min Act: -0.0002

Data Index: 36566 (C4 (Web Text))

Max Activating Token Index: 555

Text #11

Max Range: 0.7737. Min Range: -0.7737

Max Act: 0.5866. Min Act: -0.0003

Data Index: 957009 (C4 (Web Text))

Max Activating Token Index: 617

Text #12

Max Range: 0.7737. Min Range: -0.7737

Max Act: 0.5847. Min Act: -0.0002

Data Index: 852582 (C4 (Web Text))

Max Activating Token Index: 509

Text #13

Max Range: 0.7737. Min Range: -0.7737

Max Act: 0.5657. Min Act: -0.0002

Data Index: 750943 (C4 (Web Text))

Max Activating Token Index: 16

Text #14

Max Range: 0.7737. Min Range: -0.7737

Max Act: 0.5569. Min Act: -0.0002

Data Index: 1235901 (C4 (Web Text))

Max Activating Token Index: 201

Text #15

Max Range: 0.7737. Min Range: -0.7737

Max Act: 0.5702. Min Act: -0.0003

Data Index: 816469 (C4 (Web Text))

Max Activating Token Index: 738

Text #16

Max Range: 0.7737. Min Range: -0.7737

Max Act: 0.5704. Min Act: -0.0003

Data Index: 763380 (C4 (Web Text))

Max Activating Token Index: 169

Text #17

Max Range: 0.7737. Min Range: -0.7737

Max Act: 0.5791. Min Act: -0.0002

Data Index: 675339 (C4 (Web Text))

Max Activating Token Index: 66

Text #18

Max Range: 0.7737. Min Range: -0.7737

Max Act: 0.5381. Min Act: -0.0002

Data Index: 1067804 (C4 (Web Text))

Max Activating Token Index: 328

Text #19

Max Range: 0.7737. Min Range: -0.7737

Max Act: 0.5600. Min Act: -0.0002

Data Index: 1008894 (C4 (Web Text))

Max Activating Token Index: 814