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

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

Neuron 3503 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: 4.3855. Min Range: -4.3855

Max Act: 4.3855. Min Act: -0.0000

Data Index: 842377 (C4 (Web Text))

Max Activating Token Index: 651

Text #1

Max Range: 4.3855. Min Range: -4.3855

Max Act: 3.6365. Min Act: -0.0000

Data Index: 1354475 (C4 (Web Text))

Max Activating Token Index: 145

Text #2

Max Range: 4.3855. Min Range: -4.3855

Max Act: 3.5483. Min Act: -0.0000

Data Index: 724432 (C4 (Web Text))

Max Activating Token Index: 454

Text #3

Max Range: 4.3855. Min Range: -4.3855

Max Act: 3.1899. Min Act: -0.0000

Data Index: 1044945 (C4 (Web Text))

Max Activating Token Index: 782

Text #4

Max Range: 4.3855. Min Range: -4.3855

Max Act: 3.3281. Min Act: -0.0000

Data Index: 761557 (C4 (Web Text))

Max Activating Token Index: 540

Text #5

Max Range: 4.3855. Min Range: -4.3855

Max Act: 3.3616. Min Act: -0.0000

Data Index: 1154165 (C4 (Web Text))

Max Activating Token Index: 707

Text #6

Max Range: 4.3855. Min Range: -4.3855

Max Act: 3.2808. Min Act: -0.0000

Data Index: 767496 (C4 (Web Text))

Max Activating Token Index: 6

Text #7

Max Range: 4.3855. Min Range: -4.3855

Max Act: 3.2646. Min Act: -0.0000

Data Index: 402743 (C4 (Web Text))

Max Activating Token Index: 92

Text #8

Max Range: 4.3855. Min Range: -4.3855

Max Act: 3.4083. Min Act: -0.0000

Data Index: 1126142 (C4 (Web Text))

Max Activating Token Index: 130

Text #9

Max Range: 4.3855. Min Range: -4.3855

Max Act: 3.0635. Min Act: -0.0000

Data Index: 859848 (C4 (Web Text))

Max Activating Token Index: 160

Text #10

Max Range: 4.3855. Min Range: -4.3855

Max Act: 3.1454. Min Act: -0.0000

Data Index: 1293787 (C4 (Web Text))

Max Activating Token Index: 264

Text #11

Max Range: 4.3855. Min Range: -4.3855

Max Act: 3.1110. Min Act: -0.0000

Data Index: 1631203 (Python Code)

Max Activating Token Index: 946

Text #12

Max Range: 4.3855. Min Range: -4.3855

Max Act: 3.1033. Min Act: -0.0000

Data Index: 1037104 (C4 (Web Text))

Max Activating Token Index: 594

Text #13

Max Range: 4.3855. Min Range: -4.3855

Max Act: 3.0662. Min Act: -0.0000

Data Index: 407247 (C4 (Web Text))

Max Activating Token Index: 137

Text #14

Max Range: 4.3855. Min Range: -4.3855

Max Act: 3.0644. Min Act: -0.0000

Data Index: 23874 (C4 (Web Text))

Max Activating Token Index: 635

Text #15

Max Range: 4.3855. Min Range: -4.3855

Max Act: 2.8363. Min Act: -0.0000

Data Index: 92161 (C4 (Web Text))

Max Activating Token Index: 860

Text #16

Max Range: 4.3855. Min Range: -4.3855

Max Act: 2.8888. Min Act: -0.0000

Data Index: 1549324 (Python Code)

Max Activating Token Index: 634

Text #17

Max Range: 4.3855. Min Range: -4.3855

Max Act: 3.0449. Min Act: -0.0000

Data Index: 879691 (C4 (Web Text))

Max Activating Token Index: 139

Text #18

Max Range: 4.3855. Min Range: -4.3855

Max Act: 3.1862. Min Act: -0.0000

Data Index: 404431 (C4 (Web Text))

Max Activating Token Index: 723

Text #19

Max Range: 4.3855. Min Range: -4.3855

Max Act: 2.9766. Min Act: -0.0000

Data Index: 1637889 (Python Code)

Max Activating Token Index: 167