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

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

Neuron 4055 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4049. Min Range: -2.4049

Max Act: 2.4049. Min Act: -0.0000

Data Index: 1321514 (C4 (Web Text))

Max Activating Token Index: 513

Text #1

Max Range: 2.4049. Min Range: -2.4049

Max Act: 2.1694. Min Act: -0.0000

Data Index: 958820 (C4 (Web Text))

Max Activating Token Index: 155

Text #2

Max Range: 2.4049. Min Range: -2.4049

Max Act: 1.9614. Min Act: -0.0000

Data Index: 532874 (C4 (Web Text))

Max Activating Token Index: 821

Text #3

Max Range: 2.4049. Min Range: -2.4049

Max Act: 1.7251. Min Act: -0.0000

Data Index: 777536 (C4 (Web Text))

Max Activating Token Index: 459

Text #4

Max Range: 2.4049. Min Range: -2.4049

Max Act: 1.6189. Min Act: -0.0000

Data Index: 1230589 (C4 (Web Text))

Max Activating Token Index: 635

Text #5

Max Range: 2.4049. Min Range: -2.4049

Max Act: 1.6108. Min Act: -0.0000

Data Index: 616127 (C4 (Web Text))

Max Activating Token Index: 626

Text #6

Max Range: 2.4049. Min Range: -2.4049

Max Act: 1.5981. Min Act: -0.0000

Data Index: 230991 (C4 (Web Text))

Max Activating Token Index: 710

Text #7

Max Range: 2.4049. Min Range: -2.4049

Max Act: 1.4226. Min Act: -0.0000

Data Index: 195393 (C4 (Web Text))

Max Activating Token Index: 60

Text #8

Max Range: 2.4049. Min Range: -2.4049

Max Act: 1.3396. Min Act: -0.0000

Data Index: 544453 (C4 (Web Text))

Max Activating Token Index: 369

Text #9

Max Range: 2.4049. Min Range: -2.4049

Max Act: 1.4114. Min Act: -0.0000

Data Index: 525667 (C4 (Web Text))

Max Activating Token Index: 653

Text #10

Max Range: 2.4049. Min Range: -2.4049

Max Act: 1.4849. Min Act: -0.0000

Data Index: 1728 (C4 (Web Text))

Max Activating Token Index: 227

Text #11

Max Range: 2.4049. Min Range: -2.4049

Max Act: 1.4649. Min Act: -0.0000

Data Index: 303887 (C4 (Web Text))

Max Activating Token Index: 830

Text #12

Max Range: 2.4049. Min Range: -2.4049

Max Act: 1.4622. Min Act: -0.0000

Data Index: 932218 (C4 (Web Text))

Max Activating Token Index: 893

Text #13

Max Range: 2.4049. Min Range: -2.4049

Max Act: 1.3910. Min Act: -0.0000

Data Index: 1298027 (C4 (Web Text))

Max Activating Token Index: 563

Text #14

Max Range: 2.4049. Min Range: -2.4049

Max Act: 1.3857. Min Act: -0.0000

Data Index: 457087 (C4 (Web Text))

Max Activating Token Index: 989

Text #15

Max Range: 2.4049. Min Range: -2.4049

Max Act: 1.3801. Min Act: -0.0000

Data Index: 27094 (C4 (Web Text))

Max Activating Token Index: 533

Text #16

Max Range: 2.4049. Min Range: -2.4049

Max Act: 1.3499. Min Act: -0.0000

Data Index: 1101717 (C4 (Web Text))

Max Activating Token Index: 334

Text #17

Max Range: 2.4049. Min Range: -2.4049

Max Act: 1.3488. Min Act: -0.0000

Data Index: 1321053 (C4 (Web Text))

Max Activating Token Index: 892

Text #18

Max Range: 2.4049. Min Range: -2.4049

Max Act: 1.3217. Min Act: -0.0000

Data Index: 1231924 (C4 (Web Text))

Max Activating Token Index: 493

Text #19

Max Range: 2.4049. Min Range: -2.4049

Max Act: 1.2659. Min Act: -0.0000

Data Index: 1065687 (C4 (Web Text))

Max Activating Token Index: 770