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

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

Neuron 3472 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: 2.0793. Min Range: -2.0793

Max Act: 2.0420. Min Act: -0.0000

Data Index: 885158 (C4 (Web Text))

Max Activating Token Index: 282

Text #1

Max Range: 2.0793. Min Range: -2.0793

Max Act: 2.0793. Min Act: -0.0000

Data Index: 233979 (C4 (Web Text))

Max Activating Token Index: 42

Text #2

Max Range: 2.0793. Min Range: -2.0793

Max Act: 1.8197. Min Act: -0.0000

Data Index: 705382 (C4 (Web Text))

Max Activating Token Index: 79

Text #3

Max Range: 2.0793. Min Range: -2.0793

Max Act: 1.8992. Min Act: -0.0000

Data Index: 1004860 (C4 (Web Text))

Max Activating Token Index: 973

Text #4

Max Range: 2.0793. Min Range: -2.0793

Max Act: 1.6749. Min Act: -0.0000

Data Index: 208926 (C4 (Web Text))

Max Activating Token Index: 788

Text #5

Max Range: 2.0793. Min Range: -2.0793

Max Act: 1.6319. Min Act: -0.0000

Data Index: 1185713 (C4 (Web Text))

Max Activating Token Index: 778

Text #6

Max Range: 2.0793. Min Range: -2.0793

Max Act: 1.6043. Min Act: -0.0000

Data Index: 154153 (C4 (Web Text))

Max Activating Token Index: 935

Text #7

Max Range: 2.0793. Min Range: -2.0793

Max Act: 1.5101. Min Act: -0.0000

Data Index: 1288612 (C4 (Web Text))

Max Activating Token Index: 978

Text #8

Max Range: 2.0793. Min Range: -2.0793

Max Act: 1.5102. Min Act: -0.0000

Data Index: 135418 (C4 (Web Text))

Max Activating Token Index: 863

Text #9

Max Range: 2.0793. Min Range: -2.0793

Max Act: 1.4460. Min Act: -0.0000

Data Index: 473347 (C4 (Web Text))

Max Activating Token Index: 933

Text #10

Max Range: 2.0793. Min Range: -2.0793

Max Act: 1.3475. Min Act: -0.0000

Data Index: 1202495 (C4 (Web Text))

Max Activating Token Index: 38

Text #11

Max Range: 2.0793. Min Range: -2.0793

Max Act: 1.3948. Min Act: -0.0000

Data Index: 1035532 (C4 (Web Text))

Max Activating Token Index: 828

Text #12

Max Range: 2.0793. Min Range: -2.0793

Max Act: 1.3083. Min Act: -0.0000

Data Index: 1228462 (C4 (Web Text))

Max Activating Token Index: 659

Text #13

Max Range: 2.0793. Min Range: -2.0793

Max Act: 1.3740. Min Act: -0.0000

Data Index: 43131 (C4 (Web Text))

Max Activating Token Index: 390

Text #14

Max Range: 2.0793. Min Range: -2.0793

Max Act: 1.2823. Min Act: -0.0000

Data Index: 325774 (C4 (Web Text))

Max Activating Token Index: 283

Text #15

Max Range: 2.0793. Min Range: -2.0793

Max Act: 1.3533. Min Act: -0.0000

Data Index: 67736 (C4 (Web Text))

Max Activating Token Index: 894

Text #16

Max Range: 2.0793. Min Range: -2.0793

Max Act: 1.2404. Min Act: -0.0000

Data Index: 1159158 (C4 (Web Text))

Max Activating Token Index: 674

Text #17

Max Range: 2.0793. Min Range: -2.0793

Max Act: 1.3150. Min Act: -0.0000

Data Index: 643761 (C4 (Web Text))

Max Activating Token Index: 612

Text #18

Max Range: 2.0793. Min Range: -2.0793

Max Act: 1.3914. Min Act: -0.0000

Data Index: 1012584 (C4 (Web Text))

Max Activating Token Index: 877

Text #19

Max Range: 2.0793. Min Range: -2.0793

Max Act: 1.2988. Min Act: -0.0000

Data Index: 60963 (C4 (Web Text))

Max Activating Token Index: 599