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

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

Neuron 1728 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: 2.5719. Min Range: -2.5719

Max Act: 2.5719. Min Act: -0.0000

Data Index: 787978 (C4 (Web Text))

Max Activating Token Index: 269

Text #1

Max Range: 2.5719. Min Range: -2.5719

Max Act: 2.2978. Min Act: -0.0000

Data Index: 401975 (C4 (Web Text))

Max Activating Token Index: 195

Text #2

Max Range: 2.5719. Min Range: -2.5719

Max Act: 2.2053. Min Act: -0.0000

Data Index: 221442 (C4 (Web Text))

Max Activating Token Index: 165

Text #3

Max Range: 2.5719. Min Range: -2.5719

Max Act: 2.2452. Min Act: -0.0000

Data Index: 628442 (C4 (Web Text))

Max Activating Token Index: 67

Text #4

Max Range: 2.5719. Min Range: -2.5719

Max Act: 2.0127. Min Act: -0.0000

Data Index: 784766 (C4 (Web Text))

Max Activating Token Index: 148

Text #5

Max Range: 2.5719. Min Range: -2.5719

Max Act: 2.1003. Min Act: -0.0000

Data Index: 234724 (C4 (Web Text))

Max Activating Token Index: 61

Text #6

Max Range: 2.5719. Min Range: -2.5719

Max Act: 2.0293. Min Act: -0.0000

Data Index: 1209434 (C4 (Web Text))

Max Activating Token Index: 611

Text #7

Max Range: 2.5719. Min Range: -2.5719

Max Act: 1.8836. Min Act: -0.0000

Data Index: 799886 (C4 (Web Text))

Max Activating Token Index: 562

Text #8

Max Range: 2.5719. Min Range: -2.5719

Max Act: 1.9681. Min Act: -0.0000

Data Index: 1077069 (C4 (Web Text))

Max Activating Token Index: 594

Text #9

Max Range: 2.5719. Min Range: -2.5719

Max Act: 1.9746. Min Act: -0.0000

Data Index: 939614 (C4 (Web Text))

Max Activating Token Index: 540

Text #10

Max Range: 2.5719. Min Range: -2.5719

Max Act: 2.0637. Min Act: -0.0000

Data Index: 759081 (C4 (Web Text))

Max Activating Token Index: 21

Text #11

Max Range: 2.5719. Min Range: -2.5719

Max Act: 1.9101. Min Act: -0.0000

Data Index: 549696 (C4 (Web Text))

Max Activating Token Index: 272

Text #12

Max Range: 2.5719. Min Range: -2.5719

Max Act: 1.8903. Min Act: -0.0000

Data Index: 1641901 (Python Code)

Max Activating Token Index: 209

Text #13

Max Range: 2.5719. Min Range: -2.5719

Max Act: 1.9582. Min Act: -0.0000

Data Index: 467303 (C4 (Web Text))

Max Activating Token Index: 14

Text #14

Max Range: 2.5719. Min Range: -2.5719

Max Act: 1.8442. Min Act: -0.0000

Data Index: 297752 (C4 (Web Text))

Max Activating Token Index: 502

Text #15

Max Range: 2.5719. Min Range: -2.5719

Max Act: 1.6574. Min Act: -0.0000

Data Index: 820842 (C4 (Web Text))

Max Activating Token Index: 58

Text #16

Max Range: 2.5719. Min Range: -2.5719

Max Act: 1.9535. Min Act: -0.0000

Data Index: 640888 (C4 (Web Text))

Max Activating Token Index: 291

Text #17

Max Range: 2.5719. Min Range: -2.5719

Max Act: 1.8483. Min Act: -0.0000

Data Index: 1188250 (C4 (Web Text))

Max Activating Token Index: 582

Text #18

Max Range: 2.5719. Min Range: -2.5719

Max Act: 1.8306. Min Act: -0.0000

Data Index: 1555462 (Python Code)

Max Activating Token Index: 25

Text #19

Max Range: 2.5719. Min Range: -2.5719

Max Act: 1.7194. Min Act: -0.0000

Data Index: 1647895 (Python Code)

Max Activating Token Index: 43