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

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

Neuron 5708 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5309. Min Range: -1.5309

Max Act: 1.5309. Min Act: -0.0000

Data Index: 265062 (C4 (Web Text))

Max Activating Token Index: 551

Text #1

Max Range: 1.5309. Min Range: -1.5309

Max Act: 1.3738. Min Act: -0.0000

Data Index: 606819 (C4 (Web Text))

Max Activating Token Index: 189

Text #2

Max Range: 1.5309. Min Range: -1.5309

Max Act: 1.1900. Min Act: 0.0001

Data Index: 992067 (C4 (Web Text))

Max Activating Token Index: 179

Text #3

Max Range: 1.5309. Min Range: -1.5309

Max Act: 1.1059. Min Act: -0.0000

Data Index: 1299596 (C4 (Web Text))

Max Activating Token Index: 472

Text #4

Max Range: 1.5309. Min Range: -1.5309

Max Act: 1.1068. Min Act: -0.0000

Data Index: 1310581 (C4 (Web Text))

Max Activating Token Index: 494

Text #5

Max Range: 1.5309. Min Range: -1.5309

Max Act: 1.0312. Min Act: -0.0000

Data Index: 310462 (C4 (Web Text))

Max Activating Token Index: 985

Text #6

Max Range: 1.5309. Min Range: -1.5309

Max Act: 1.0232. Min Act: 0.0000

Data Index: 901537 (C4 (Web Text))

Max Activating Token Index: 816

Text #7

Max Range: 1.5309. Min Range: -1.5309

Max Act: 1.0055. Min Act: -0.0000

Data Index: 576046 (C4 (Web Text))

Max Activating Token Index: 125

Text #8

Max Range: 1.5309. Min Range: -1.5309

Max Act: 0.9375. Min Act: 0.0000

Data Index: 623670 (C4 (Web Text))

Max Activating Token Index: 904

Text #9

Max Range: 1.5309. Min Range: -1.5309

Max Act: 1.0604. Min Act: -0.0000

Data Index: 952121 (C4 (Web Text))

Max Activating Token Index: 828

Text #10

Max Range: 1.5309. Min Range: -1.5309

Max Act: 0.9164. Min Act: -0.0000

Data Index: 898693 (C4 (Web Text))

Max Activating Token Index: 804

Text #11

Max Range: 1.5309. Min Range: -1.5309

Max Act: 0.9715. Min Act: -0.0000

Data Index: 855265 (C4 (Web Text))

Max Activating Token Index: 66

Text #12

Max Range: 1.5309. Min Range: -1.5309

Max Act: 0.9627. Min Act: 0.0000

Data Index: 51129 (C4 (Web Text))

Max Activating Token Index: 710

Text #13

Max Range: 1.5309. Min Range: -1.5309

Max Act: 0.9413. Min Act: -0.0000

Data Index: 1217309 (C4 (Web Text))

Max Activating Token Index: 499

Text #14

Max Range: 1.5309. Min Range: -1.5309

Max Act: 0.9963. Min Act: -0.0000

Data Index: 1009194 (C4 (Web Text))

Max Activating Token Index: 697

Text #15

Max Range: 1.5309. Min Range: -1.5309

Max Act: 0.9232. Min Act: 0.0001

Data Index: 545502 (C4 (Web Text))

Max Activating Token Index: 26

Text #16

Max Range: 1.5309. Min Range: -1.5309

Max Act: 0.9089. Min Act: -0.0000

Data Index: 37672 (C4 (Web Text))

Max Activating Token Index: 904

Text #17

Max Range: 1.5309. Min Range: -1.5309

Max Act: 0.9116. Min Act: -0.0000

Data Index: 381649 (C4 (Web Text))

Max Activating Token Index: 852

Text #18

Max Range: 1.5309. Min Range: -1.5309

Max Act: 0.9071. Min Act: -0.0000

Data Index: 700787 (C4 (Web Text))

Max Activating Token Index: 235

Text #19

Max Range: 1.5309. Min Range: -1.5309

Max Act: 0.9045. Min Act: 0.0000

Data Index: 259716 (C4 (Web Text))

Max Activating Token Index: 94