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

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

Neuron 447 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: 1.3985. Min Range: -1.3985

Max Act: 1.3161. Min Act: -0.0000

Data Index: 1226588 (C4 (Web Text))

Max Activating Token Index: 434

Text #1

Max Range: 1.3985. Min Range: -1.3985

Max Act: 1.3985. Min Act: -0.0000

Data Index: 445919 (C4 (Web Text))

Max Activating Token Index: 449

Text #2

Max Range: 1.3985. Min Range: -1.3985

Max Act: 1.1862. Min Act: -0.0000

Data Index: 1051999 (C4 (Web Text))

Max Activating Token Index: 645

Text #3

Max Range: 1.3985. Min Range: -1.3985

Max Act: 1.2208. Min Act: -0.0000

Data Index: 890094 (C4 (Web Text))

Max Activating Token Index: 556

Text #4

Max Range: 1.3985. Min Range: -1.3985

Max Act: 1.1745. Min Act: -0.0000

Data Index: 420119 (C4 (Web Text))

Max Activating Token Index: 712

Text #5

Max Range: 1.3985. Min Range: -1.3985

Max Act: 1.1988. Min Act: -0.0000

Data Index: 334957 (C4 (Web Text))

Max Activating Token Index: 790

Text #6

Max Range: 1.3985. Min Range: -1.3985

Max Act: 1.2095. Min Act: -0.0000

Data Index: 1287680 (C4 (Web Text))

Max Activating Token Index: 226

Text #7

Max Range: 1.3985. Min Range: -1.3985

Max Act: 1.1616. Min Act: -0.0000

Data Index: 419547 (C4 (Web Text))

Max Activating Token Index: 439

Text #8

Max Range: 1.3985. Min Range: -1.3985

Max Act: 1.0999. Min Act: -0.0000

Data Index: 749974 (C4 (Web Text))

Max Activating Token Index: 787

Text #9

Max Range: 1.3985. Min Range: -1.3985

Max Act: 1.1239. Min Act: -0.0000

Data Index: 65173 (C4 (Web Text))

Max Activating Token Index: 133

Text #10

Max Range: 1.3985. Min Range: -1.3985

Max Act: 1.0883. Min Act: -0.0000

Data Index: 1001945 (C4 (Web Text))

Max Activating Token Index: 424

Text #11

Max Range: 1.3985. Min Range: -1.3985

Max Act: 1.0897. Min Act: -0.0000

Data Index: 513093 (C4 (Web Text))

Max Activating Token Index: 95

Text #12

Max Range: 1.3985. Min Range: -1.3985

Max Act: 1.0109. Min Act: -0.0000

Data Index: 1175269 (C4 (Web Text))

Max Activating Token Index: 586

Text #13

Max Range: 1.3985. Min Range: -1.3985

Max Act: 0.9236. Min Act: -0.0000

Data Index: 1495181 (Python Code)

Max Activating Token Index: 936

Text #14

Max Range: 1.3985. Min Range: -1.3985

Max Act: 0.9776. Min Act: -0.0000

Data Index: 1402300 (Python Code)

Max Activating Token Index: 455

Text #15

Max Range: 1.3985. Min Range: -1.3985

Max Act: 0.9190. Min Act: -0.0000

Data Index: 906932 (C4 (Web Text))

Max Activating Token Index: 243

Text #16

Max Range: 1.3985. Min Range: -1.3985

Max Act: 0.9714. Min Act: -0.0000

Data Index: 1334890 (C4 (Web Text))

Max Activating Token Index: 263

Text #17

Max Range: 1.3985. Min Range: -1.3985

Max Act: 0.9478. Min Act: -0.0000

Data Index: 1492806 (Python Code)

Max Activating Token Index: 131

Text #18

Max Range: 1.3985. Min Range: -1.3985

Max Act: 0.9449. Min Act: -0.0000

Data Index: 1288967 (C4 (Web Text))

Max Activating Token Index: 432

Text #19

Max Range: 1.3985. Min Range: -1.3985

Max Act: 0.8669. Min Act: -0.0000

Data Index: 56072 (C4 (Web Text))

Max Activating Token Index: 618