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

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

Neuron 5902 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5449. Min Range: -0.5449

Max Act: 0.5449. Min Act: -0.0000

Data Index: 1009311 (C4 (Web Text))

Max Activating Token Index: 961

Text #1

Max Range: 0.5449. Min Range: -0.5449

Max Act: 0.5318. Min Act: -0.0000

Data Index: 198252 (C4 (Web Text))

Max Activating Token Index: 848

Text #2

Max Range: 0.5449. Min Range: -0.5449

Max Act: 0.4821. Min Act: -0.0000

Data Index: 734334 (C4 (Web Text))

Max Activating Token Index: 466

Text #3

Max Range: 0.5449. Min Range: -0.5449

Max Act: 0.4603. Min Act: -0.0000

Data Index: 1192712 (C4 (Web Text))

Max Activating Token Index: 462

Text #4

Max Range: 0.5449. Min Range: -0.5449

Max Act: 0.4225. Min Act: -0.0000

Data Index: 984052 (C4 (Web Text))

Max Activating Token Index: 871

Text #5

Max Range: 0.5449. Min Range: -0.5449

Max Act: 0.4304. Min Act: -0.0000

Data Index: 247544 (C4 (Web Text))

Max Activating Token Index: 447

Text #6

Max Range: 0.5449. Min Range: -0.5449

Max Act: 0.4023. Min Act: -0.0000

Data Index: 351769 (C4 (Web Text))

Max Activating Token Index: 480

Text #7

Max Range: 0.5449. Min Range: -0.5449

Max Act: 0.4033. Min Act: -0.0000

Data Index: 530539 (C4 (Web Text))

Max Activating Token Index: 848

Text #8

Max Range: 0.5449. Min Range: -0.5449

Max Act: 0.3955. Min Act: -0.0000

Data Index: 1351030 (C4 (Web Text))

Max Activating Token Index: 799

Text #9

Max Range: 0.5449. Min Range: -0.5449

Max Act: 0.4170. Min Act: -0.0000

Data Index: 1054099 (C4 (Web Text))

Max Activating Token Index: 480

Text #10

Max Range: 0.5449. Min Range: -0.5449

Max Act: 0.3975. Min Act: -0.0000

Data Index: 547470 (C4 (Web Text))

Max Activating Token Index: 965

Text #11

Max Range: 0.5449. Min Range: -0.5449

Max Act: 0.4125. Min Act: -0.0000

Data Index: 409024 (C4 (Web Text))

Max Activating Token Index: 369

Text #12

Max Range: 0.5449. Min Range: -0.5449

Max Act: 0.4015. Min Act: -0.0000

Data Index: 535890 (C4 (Web Text))

Max Activating Token Index: 285

Text #13

Max Range: 0.5449. Min Range: -0.5449

Max Act: 0.4100. Min Act: -0.0000

Data Index: 708542 (C4 (Web Text))

Max Activating Token Index: 713

Text #14

Max Range: 0.5449. Min Range: -0.5449

Max Act: 0.3766. Min Act: -0.0000

Data Index: 398197 (C4 (Web Text))

Max Activating Token Index: 724

Text #15

Max Range: 0.5449. Min Range: -0.5449

Max Act: 0.3853. Min Act: -0.0000

Data Index: 64684 (C4 (Web Text))

Max Activating Token Index: 715

Text #16

Max Range: 0.5449. Min Range: -0.5449

Max Act: 0.3737. Min Act: -0.0000

Data Index: 330790 (C4 (Web Text))

Max Activating Token Index: 640

Text #17

Max Range: 0.5449. Min Range: -0.5449

Max Act: 0.3855. Min Act: -0.0000

Data Index: 457620 (C4 (Web Text))

Max Activating Token Index: 420

Text #18

Max Range: 0.5449. Min Range: -0.5449

Max Act: 0.3713. Min Act: -0.0000

Data Index: 524876 (C4 (Web Text))

Max Activating Token Index: 685

Text #19

Max Range: 0.5449. Min Range: -0.5449

Max Act: 0.3528. Min Act: -0.0000

Data Index: 1231628 (C4 (Web Text))

Max Activating Token Index: 900