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

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

Neuron 724 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4495. Min Range: -2.4495

Max Act: 2.3461. Min Act: -0.0000

Data Index: 1510212 (Python Code)

Max Activating Token Index: 929

Text #1

Max Range: 2.4495. Min Range: -2.4495

Max Act: 2.4495. Min Act: -0.0000

Data Index: 259302 (C4 (Web Text))

Max Activating Token Index: 1015

Text #2

Max Range: 2.4495. Min Range: -2.4495

Max Act: 2.2642. Min Act: -0.0000

Data Index: 638114 (C4 (Web Text))

Max Activating Token Index: 891

Text #3

Max Range: 2.4495. Min Range: -2.4495

Max Act: 2.3714. Min Act: -0.0000

Data Index: 945990 (C4 (Web Text))

Max Activating Token Index: 1012

Text #4

Max Range: 2.4495. Min Range: -2.4495

Max Act: 2.4371. Min Act: -0.0000

Data Index: 807583 (C4 (Web Text))

Max Activating Token Index: 450

Text #5

Max Range: 2.4495. Min Range: -2.4495

Max Act: 2.2838. Min Act: -0.0000

Data Index: 937358 (C4 (Web Text))

Max Activating Token Index: 845

Text #6

Max Range: 2.4495. Min Range: -2.4495

Max Act: 2.2176. Min Act: -0.0000

Data Index: 389393 (C4 (Web Text))

Max Activating Token Index: 941

Text #7

Max Range: 2.4495. Min Range: -2.4495

Max Act: 2.2096. Min Act: -0.0000

Data Index: 674416 (C4 (Web Text))

Max Activating Token Index: 389

Text #8

Max Range: 2.4495. Min Range: -2.4495

Max Act: 2.2550. Min Act: -0.0000

Data Index: 1357037 (C4 (Web Text))

Max Activating Token Index: 621

Text #9

Max Range: 2.4495. Min Range: -2.4495

Max Act: 2.2125. Min Act: -0.0000

Data Index: 528208 (C4 (Web Text))

Max Activating Token Index: 810

Text #10

Max Range: 2.4495. Min Range: -2.4495

Max Act: 2.3561. Min Act: -0.0000

Data Index: 1037661 (C4 (Web Text))

Max Activating Token Index: 529

Text #11

Max Range: 2.4495. Min Range: -2.4495

Max Act: 2.2067. Min Act: -0.0000

Data Index: 1347781 (C4 (Web Text))

Max Activating Token Index: 930

Text #12

Max Range: 2.4495. Min Range: -2.4495

Max Act: 2.2070. Min Act: -0.0000

Data Index: 1272644 (C4 (Web Text))

Max Activating Token Index: 867

Text #13

Max Range: 2.4495. Min Range: -2.4495

Max Act: 2.0594. Min Act: -0.0000

Data Index: 1405685 (Python Code)

Max Activating Token Index: 27

Text #14

Max Range: 2.4495. Min Range: -2.4495

Max Act: 2.1687. Min Act: -0.0000

Data Index: 184732 (C4 (Web Text))

Max Activating Token Index: 426

Text #15

Max Range: 2.4495. Min Range: -2.4495

Max Act: 2.0042. Min Act: -0.0000

Data Index: 884371 (C4 (Web Text))

Max Activating Token Index: 644

Text #16

Max Range: 2.4495. Min Range: -2.4495

Max Act: 2.0865. Min Act: -0.0000

Data Index: 75281 (C4 (Web Text))

Max Activating Token Index: 755

Text #17

Max Range: 2.4495. Min Range: -2.4495

Max Act: 2.0374. Min Act: -0.0000

Data Index: 576699 (C4 (Web Text))

Max Activating Token Index: 657

Text #18

Max Range: 2.4495. Min Range: -2.4495

Max Act: 2.0993. Min Act: -0.0000

Data Index: 689875 (C4 (Web Text))

Max Activating Token Index: 380

Text #19

Max Range: 2.4495. Min Range: -2.4495

Max Act: 2.2098. Min Act: -0.0000

Data Index: 394403 (C4 (Web Text))

Max Activating Token Index: 815