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

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

Neuron 1002 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7704. Min Range: -0.7704

Max Act: 0.7704. Min Act: -0.0000

Data Index: 641831 (C4 (Web Text))

Max Activating Token Index: 670

Text #1

Max Range: 0.7704. Min Range: -0.7704

Max Act: 0.6840. Min Act: -0.0000

Data Index: 240454 (C4 (Web Text))

Max Activating Token Index: 57

Text #2

Max Range: 0.7704. Min Range: -0.7704

Max Act: 0.7043. Min Act: -0.0000

Data Index: 1148556 (C4 (Web Text))

Max Activating Token Index: 424

Text #3

Max Range: 0.7704. Min Range: -0.7704

Max Act: 0.6128. Min Act: -0.0000

Data Index: 1320418 (C4 (Web Text))

Max Activating Token Index: 563

Text #4

Max Range: 0.7704. Min Range: -0.7704

Max Act: 0.6024. Min Act: -0.0000

Data Index: 89631 (C4 (Web Text))

Max Activating Token Index: 145

Text #5

Max Range: 0.7704. Min Range: -0.7704

Max Act: 0.4927. Min Act: -0.0000

Data Index: 1264867 (C4 (Web Text))

Max Activating Token Index: 1006

Text #6

Max Range: 0.7704. Min Range: -0.7704

Max Act: 0.5042. Min Act: -0.0000

Data Index: 1293157 (C4 (Web Text))

Max Activating Token Index: 389

Text #7

Max Range: 0.7704. Min Range: -0.7704

Max Act: 0.5860. Min Act: -0.0000

Data Index: 865823 (C4 (Web Text))

Max Activating Token Index: 813

Text #8

Max Range: 0.7704. Min Range: -0.7704

Max Act: 0.5562. Min Act: -0.0000

Data Index: 1292826 (C4 (Web Text))

Max Activating Token Index: 453

Text #9

Max Range: 0.7704. Min Range: -0.7704

Max Act: 0.4989. Min Act: -0.0000

Data Index: 115917 (C4 (Web Text))

Max Activating Token Index: 875

Text #10

Max Range: 0.7704. Min Range: -0.7704

Max Act: 0.5263. Min Act: -0.0000

Data Index: 1248858 (C4 (Web Text))

Max Activating Token Index: 109

Text #11

Max Range: 0.7704. Min Range: -0.7704

Max Act: 0.5306. Min Act: -0.0000

Data Index: 740512 (C4 (Web Text))

Max Activating Token Index: 474

Text #12

Max Range: 0.7704. Min Range: -0.7704

Max Act: 0.4431. Min Act: -0.0000

Data Index: 465596 (C4 (Web Text))

Max Activating Token Index: 878

Text #13

Max Range: 0.7704. Min Range: -0.7704

Max Act: 0.4856. Min Act: -0.0000

Data Index: 750892 (C4 (Web Text))

Max Activating Token Index: 394

Text #14

Max Range: 0.7704. Min Range: -0.7704

Max Act: 0.4854. Min Act: -0.0000

Data Index: 237605 (C4 (Web Text))

Max Activating Token Index: 255

Text #15

Max Range: 0.7704. Min Range: -0.7704

Max Act: 0.4754. Min Act: -0.0000

Data Index: 1346084 (C4 (Web Text))

Max Activating Token Index: 697

Text #16

Max Range: 0.7704. Min Range: -0.7704

Max Act: 0.4772. Min Act: -0.0000

Data Index: 589561 (C4 (Web Text))

Max Activating Token Index: 975

Text #17

Max Range: 0.7704. Min Range: -0.7704

Max Act: 0.4515. Min Act: -0.0000

Data Index: 551354 (C4 (Web Text))

Max Activating Token Index: 670

Text #18

Max Range: 0.7704. Min Range: -0.7704

Max Act: 0.4855. Min Act: -0.0000

Data Index: 363186 (C4 (Web Text))

Max Activating Token Index: 454

Text #19

Max Range: 0.7704. Min Range: -0.7704

Max Act: 0.4888. Min Act: -0.0000

Data Index: 1134398 (C4 (Web Text))

Max Activating Token Index: 478