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

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

Neuron 5408 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: 1.4584. Min Range: -1.4584

Max Act: 1.4242. Min Act: -0.0000

Data Index: 1055651 (C4 (Web Text))

Max Activating Token Index: 480

Text #1

Max Range: 1.4584. Min Range: -1.4584

Max Act: 1.4584. Min Act: -0.0000

Data Index: 224642 (C4 (Web Text))

Max Activating Token Index: 885

Text #2

Max Range: 1.4584. Min Range: -1.4584

Max Act: 1.1049. Min Act: -0.0000

Data Index: 255414 (C4 (Web Text))

Max Activating Token Index: 985

Text #3

Max Range: 1.4584. Min Range: -1.4584

Max Act: 1.0519. Min Act: -0.0000

Data Index: 710784 (C4 (Web Text))

Max Activating Token Index: 528

Text #4

Max Range: 1.4584. Min Range: -1.4584

Max Act: 0.9814. Min Act: -0.0000

Data Index: 1443692 (Python Code)

Max Activating Token Index: 871

Text #5

Max Range: 1.4584. Min Range: -1.4584

Max Act: 0.9794. Min Act: -0.0000

Data Index: 1261277 (C4 (Web Text))

Max Activating Token Index: 905

Text #6

Max Range: 1.4584. Min Range: -1.4584

Max Act: 1.1199. Min Act: -0.0000

Data Index: 685613 (C4 (Web Text))

Max Activating Token Index: 948

Text #7

Max Range: 1.4584. Min Range: -1.4584

Max Act: 0.9008. Min Act: -0.0000

Data Index: 1538574 (Python Code)

Max Activating Token Index: 563

Text #8

Max Range: 1.4584. Min Range: -1.4584

Max Act: 0.9906. Min Act: -0.0000

Data Index: 634226 (C4 (Web Text))

Max Activating Token Index: 199

Text #9

Max Range: 1.4584. Min Range: -1.4584

Max Act: 0.8019. Min Act: -0.0000

Data Index: 1118682 (C4 (Web Text))

Max Activating Token Index: 917

Text #10

Max Range: 1.4584. Min Range: -1.4584

Max Act: 0.9040. Min Act: -0.0000

Data Index: 1409625 (Python Code)

Max Activating Token Index: 162

Text #11

Max Range: 1.4584. Min Range: -1.4584

Max Act: 0.8916. Min Act: -0.0000

Data Index: 208848 (C4 (Web Text))

Max Activating Token Index: 249

Text #12

Max Range: 1.4584. Min Range: -1.4584

Max Act: 0.8433. Min Act: -0.0000

Data Index: 417058 (C4 (Web Text))

Max Activating Token Index: 496

Text #13

Max Range: 1.4584. Min Range: -1.4584

Max Act: 0.9270. Min Act: -0.0000

Data Index: 1650270 (Python Code)

Max Activating Token Index: 884

Text #14

Max Range: 1.4584. Min Range: -1.4584

Max Act: 0.8224. Min Act: -0.0000

Data Index: 919364 (C4 (Web Text))

Max Activating Token Index: 228

Text #15

Max Range: 1.4584. Min Range: -1.4584

Max Act: 0.9078. Min Act: -0.0000

Data Index: 334326 (C4 (Web Text))

Max Activating Token Index: 980

Text #16

Max Range: 1.4584. Min Range: -1.4584

Max Act: 0.8730. Min Act: -0.0000

Data Index: 462757 (C4 (Web Text))

Max Activating Token Index: 333

Text #17

Max Range: 1.4584. Min Range: -1.4584

Max Act: 0.7674. Min Act: -0.0000

Data Index: 1480384 (Python Code)

Max Activating Token Index: 189

Text #18

Max Range: 1.4584. Min Range: -1.4584

Max Act: 0.8365. Min Act: -0.0000

Data Index: 1191437 (C4 (Web Text))

Max Activating Token Index: 886

Text #19

Max Range: 1.4584. Min Range: -1.4584

Max Act: 0.7911. Min Act: -0.0000

Data Index: 1521598 (Python Code)

Max Activating Token Index: 386