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

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

Neuron 17 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.5210. Min Range: -6.5210

Max Act: 6.5210. Min Act: -0.0000

Data Index: 928796 (C4 (Web Text))

Max Activating Token Index: 840

Text #1

Max Range: 6.5210. Min Range: -6.5210

Max Act: 5.3834. Min Act: -0.0000

Data Index: 1041867 (C4 (Web Text))

Max Activating Token Index: 899

Text #2

Max Range: 6.5210. Min Range: -6.5210

Max Act: 4.9767. Min Act: -0.0000

Data Index: 980885 (C4 (Web Text))

Max Activating Token Index: 629

Text #3

Max Range: 6.5210. Min Range: -6.5210

Max Act: 4.9438. Min Act: -0.0000

Data Index: 308421 (C4 (Web Text))

Max Activating Token Index: 618

Text #4

Max Range: 6.5210. Min Range: -6.5210

Max Act: 4.7501. Min Act: -0.0000

Data Index: 1263080 (C4 (Web Text))

Max Activating Token Index: 63

Text #5

Max Range: 6.5210. Min Range: -6.5210

Max Act: 4.7432. Min Act: -0.0000

Data Index: 156793 (C4 (Web Text))

Max Activating Token Index: 971

Text #6

Max Range: 6.5210. Min Range: -6.5210

Max Act: 4.9826. Min Act: -0.0000

Data Index: 1038882 (C4 (Web Text))

Max Activating Token Index: 748

Text #7

Max Range: 6.5210. Min Range: -6.5210

Max Act: 4.6076. Min Act: -0.0000

Data Index: 1020671 (C4 (Web Text))

Max Activating Token Index: 763

Text #8

Max Range: 6.5210. Min Range: -6.5210

Max Act: 4.4061. Min Act: -0.0000

Data Index: 359180 (C4 (Web Text))

Max Activating Token Index: 766

Text #9

Max Range: 6.5210. Min Range: -6.5210

Max Act: 4.0801. Min Act: -0.0000

Data Index: 1226054 (C4 (Web Text))

Max Activating Token Index: 912

Text #10

Max Range: 6.5210. Min Range: -6.5210

Max Act: 4.3355. Min Act: -0.0000

Data Index: 814990 (C4 (Web Text))

Max Activating Token Index: 596

Text #11

Max Range: 6.5210. Min Range: -6.5210

Max Act: 3.7990. Min Act: -0.0000

Data Index: 53135 (C4 (Web Text))

Max Activating Token Index: 704

Text #12

Max Range: 6.5210. Min Range: -6.5210

Max Act: 4.0842. Min Act: -0.0000

Data Index: 321692 (C4 (Web Text))

Max Activating Token Index: 491

Text #13

Max Range: 6.5210. Min Range: -6.5210

Max Act: 3.8799. Min Act: -0.0000

Data Index: 321477 (C4 (Web Text))

Max Activating Token Index: 445

Text #14

Max Range: 6.5210. Min Range: -6.5210

Max Act: 4.0413. Min Act: -0.0000

Data Index: 333767 (C4 (Web Text))

Max Activating Token Index: 450

Text #15

Max Range: 6.5210. Min Range: -6.5210

Max Act: 4.0150. Min Act: -0.0000

Data Index: 212834 (C4 (Web Text))

Max Activating Token Index: 448

Text #16

Max Range: 6.5210. Min Range: -6.5210

Max Act: 4.2148. Min Act: -0.0000

Data Index: 35652 (C4 (Web Text))

Max Activating Token Index: 316

Text #17

Max Range: 6.5210. Min Range: -6.5210

Max Act: 3.8219. Min Act: -0.0000

Data Index: 1068945 (C4 (Web Text))

Max Activating Token Index: 101

Text #18

Max Range: 6.5210. Min Range: -6.5210

Max Act: 3.9633. Min Act: -0.0000

Data Index: 530488 (C4 (Web Text))

Max Activating Token Index: 285

Text #19

Max Range: 6.5210. Min Range: -6.5210

Max Act: 3.9671. Min Act: -0.0000

Data Index: 346154 (C4 (Web Text))

Max Activating Token Index: 406