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

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

Neuron 1016 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: 0.6796. Min Range: -0.6796

Max Act: 0.6796. Min Act: -0.0000

Data Index: 364220 (C4 (Web Text))

Max Activating Token Index: 159

Text #1

Max Range: 0.6796. Min Range: -0.6796

Max Act: 0.6224. Min Act: 0.0000

Data Index: 1044684 (C4 (Web Text))

Max Activating Token Index: 32

Text #2

Max Range: 0.6796. Min Range: -0.6796

Max Act: 0.6006. Min Act: -0.0000

Data Index: 1195308 (C4 (Web Text))

Max Activating Token Index: 444

Text #3

Max Range: 0.6796. Min Range: -0.6796

Max Act: 0.5939. Min Act: -0.0000

Data Index: 137844 (C4 (Web Text))

Max Activating Token Index: 392

Text #4

Max Range: 0.6796. Min Range: -0.6796

Max Act: 0.5432. Min Act: -0.0000

Data Index: 848128 (C4 (Web Text))

Max Activating Token Index: 118

Text #5

Max Range: 0.6796. Min Range: -0.6796

Max Act: 0.5801. Min Act: -0.0000

Data Index: 987244 (C4 (Web Text))

Max Activating Token Index: 430

Text #6

Max Range: 0.6796. Min Range: -0.6796

Max Act: 0.5563. Min Act: -0.0000

Data Index: 640629 (C4 (Web Text))

Max Activating Token Index: 34

Text #7

Max Range: 0.6796. Min Range: -0.6796

Max Act: 0.4970. Min Act: -0.0000

Data Index: 481288 (C4 (Web Text))

Max Activating Token Index: 696

Text #8

Max Range: 0.6796. Min Range: -0.6796

Max Act: 0.4669. Min Act: -0.0000

Data Index: 1044646 (C4 (Web Text))

Max Activating Token Index: 122

Text #9

Max Range: 0.6796. Min Range: -0.6796

Max Act: 0.4703. Min Act: 0.0000

Data Index: 1243704 (C4 (Web Text))

Max Activating Token Index: 158

Text #10

Max Range: 0.6796. Min Range: -0.6796

Max Act: 0.4447. Min Act: -0.0000

Data Index: 209957 (C4 (Web Text))

Max Activating Token Index: 907

Text #11

Max Range: 0.6796. Min Range: -0.6796

Max Act: 0.4220. Min Act: -0.0000

Data Index: 287262 (C4 (Web Text))

Max Activating Token Index: 55

Text #12

Max Range: 0.6796. Min Range: -0.6796

Max Act: 0.4192. Min Act: 0.0000

Data Index: 60620 (C4 (Web Text))

Max Activating Token Index: 458

Text #13

Max Range: 0.6796. Min Range: -0.6796

Max Act: 0.4020. Min Act: -0.0000

Data Index: 1337999 (C4 (Web Text))

Max Activating Token Index: 611

Text #14

Max Range: 0.6796. Min Range: -0.6796

Max Act: 0.3992. Min Act: -0.0000

Data Index: 101400 (C4 (Web Text))

Max Activating Token Index: 498

Text #15

Max Range: 0.6796. Min Range: -0.6796

Max Act: 0.4420. Min Act: -0.0000

Data Index: 64047 (C4 (Web Text))

Max Activating Token Index: 20

Text #16

Max Range: 0.6796. Min Range: -0.6796

Max Act: 0.4102. Min Act: 0.0000

Data Index: 358855 (C4 (Web Text))

Max Activating Token Index: 355

Text #17

Max Range: 0.6796. Min Range: -0.6796

Max Act: 0.4218. Min Act: -0.0000

Data Index: 49414 (C4 (Web Text))

Max Activating Token Index: 953

Text #18

Max Range: 0.6796. Min Range: -0.6796

Max Act: 0.3907. Min Act: 0.0000

Data Index: 396393 (C4 (Web Text))

Max Activating Token Index: 187

Text #19

Max Range: 0.6796. Min Range: -0.6796

Max Act: 0.4005. Min Act: -0.0000

Data Index: 89736 (C4 (Web Text))

Max Activating Token Index: 182