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

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

Neuron 3565 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2773. Min Range: -0.2773

Max Act: 0.2773. Min Act: -0.0001

Data Index: 175346 (C4 (Web Text))

Max Activating Token Index: 903

Text #1

Max Range: 0.2773. Min Range: -0.2773

Max Act: 0.2370. Min Act: -0.0000

Data Index: 946759 (C4 (Web Text))

Max Activating Token Index: 713

Text #2

Max Range: 0.2773. Min Range: -0.2773

Max Act: 0.2099. Min Act: -0.0000

Data Index: 110527 (C4 (Web Text))

Max Activating Token Index: 946

Text #3

Max Range: 0.2773. Min Range: -0.2773

Max Act: 0.1958. Min Act: -0.0000

Data Index: 534142 (C4 (Web Text))

Max Activating Token Index: 661

Text #4

Max Range: 0.2773. Min Range: -0.2773

Max Act: 0.1872. Min Act: -0.0000

Data Index: 845682 (C4 (Web Text))

Max Activating Token Index: 91

Text #5

Max Range: 0.2773. Min Range: -0.2773

Max Act: 0.1831. Min Act: -0.0000

Data Index: 435974 (C4 (Web Text))

Max Activating Token Index: 665

Text #6

Max Range: 0.2773. Min Range: -0.2773

Max Act: 0.1959. Min Act: -0.0001

Data Index: 870794 (C4 (Web Text))

Max Activating Token Index: 891

Text #7

Max Range: 0.2773. Min Range: -0.2773

Max Act: 0.1579. Min Act: -0.0000

Data Index: 887429 (C4 (Web Text))

Max Activating Token Index: 935

Text #8

Max Range: 0.2773. Min Range: -0.2773

Max Act: 0.1940. Min Act: -0.0000

Data Index: 660625 (C4 (Web Text))

Max Activating Token Index: 570

Text #9

Max Range: 0.2773. Min Range: -0.2773

Max Act: 0.1858. Min Act: -0.0000

Data Index: 133864 (C4 (Web Text))

Max Activating Token Index: 1004

Text #10

Max Range: 0.2773. Min Range: -0.2773

Max Act: 0.1775. Min Act: -0.0000

Data Index: 214403 (C4 (Web Text))

Max Activating Token Index: 70

Text #11

Max Range: 0.2773. Min Range: -0.2773

Max Act: 0.1852. Min Act: -0.0000

Data Index: 427601 (C4 (Web Text))

Max Activating Token Index: 732

Text #12

Max Range: 0.2773. Min Range: -0.2773

Max Act: 0.1710. Min Act: -0.0000

Data Index: 653561 (C4 (Web Text))

Max Activating Token Index: 558

Text #13

Max Range: 0.2773. Min Range: -0.2773

Max Act: 0.1869. Min Act: -0.0000

Data Index: 624678 (C4 (Web Text))

Max Activating Token Index: 808

Text #14

Max Range: 0.2773. Min Range: -0.2773

Max Act: 0.1793. Min Act: -0.0000

Data Index: 549565 (C4 (Web Text))

Max Activating Token Index: 428

Text #15

Max Range: 0.2773. Min Range: -0.2773

Max Act: 0.1476. Min Act: -0.0001

Data Index: 111764 (C4 (Web Text))

Max Activating Token Index: 852

Text #16

Max Range: 0.2773. Min Range: -0.2773

Max Act: 0.1657. Min Act: -0.0000

Data Index: 414555 (C4 (Web Text))

Max Activating Token Index: 397

Text #17

Max Range: 0.2773. Min Range: -0.2773

Max Act: 0.1609. Min Act: -0.0000

Data Index: 762191 (C4 (Web Text))

Max Activating Token Index: 776

Text #18

Max Range: 0.2773. Min Range: -0.2773

Max Act: 0.1634. Min Act: -0.0000

Data Index: 1138291 (C4 (Web Text))

Max Activating Token Index: 409

Text #19

Max Range: 0.2773. Min Range: -0.2773

Max Act: 0.1753. Min Act: -0.0000

Data Index: 1464062 (Python Code)

Max Activating Token Index: 965