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

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

Neuron 3515 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0878. Min Act: -0.0002

Data Index: 1126980 (C4 (Web Text))

Max Activating Token Index: 691

Text #1

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0682. Min Act: -0.0002

Data Index: 445738 (C4 (Web Text))

Max Activating Token Index: 762

Text #2

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0679. Min Act: -0.0002

Data Index: 1057977 (C4 (Web Text))

Max Activating Token Index: 932

Text #3

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0688. Min Act: -0.0002

Data Index: 1158794 (C4 (Web Text))

Max Activating Token Index: 868

Text #4

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0709. Min Act: -0.0002

Data Index: 405947 (C4 (Web Text))

Max Activating Token Index: 690

Text #5

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0700. Min Act: -0.0002

Data Index: 815436 (C4 (Web Text))

Max Activating Token Index: 900

Text #6

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0593. Min Act: -0.0002

Data Index: 470274 (C4 (Web Text))

Max Activating Token Index: 330

Text #7

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0627. Min Act: -0.0002

Data Index: 424059 (C4 (Web Text))

Max Activating Token Index: 721

Text #8

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0639. Min Act: -0.0002

Data Index: 840916 (C4 (Web Text))

Max Activating Token Index: 347

Text #9

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0644. Min Act: -0.0002

Data Index: 1138588 (C4 (Web Text))

Max Activating Token Index: 149

Text #10

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0558. Min Act: -0.0002

Data Index: 690423 (C4 (Web Text))

Max Activating Token Index: 793

Text #11

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0578. Min Act: -0.0002

Data Index: 675615 (C4 (Web Text))

Max Activating Token Index: 125

Text #12

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0520. Min Act: -0.0002

Data Index: 883354 (C4 (Web Text))

Max Activating Token Index: 732

Text #13

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0620. Min Act: -0.0002

Data Index: 222622 (C4 (Web Text))

Max Activating Token Index: 71

Text #14

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0566. Min Act: -0.0002

Data Index: 687165 (C4 (Web Text))

Max Activating Token Index: 397

Text #15

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0583. Min Act: -0.0002

Data Index: 941383 (C4 (Web Text))

Max Activating Token Index: 207

Text #16

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0566. Min Act: -0.0002

Data Index: 297282 (C4 (Web Text))

Max Activating Token Index: 45

Text #17

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0622. Min Act: -0.0002

Data Index: 717314 (C4 (Web Text))

Max Activating Token Index: 349

Text #18

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0557. Min Act: -0.0002

Data Index: 965381 (C4 (Web Text))

Max Activating Token Index: 422

Text #19

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0583. Min Act: -0.0002

Data Index: 32870 (C4 (Web Text))

Max Activating Token Index: 749