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

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

Neuron 2388 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: 1.9260. Min Range: -1.9260

Max Act: 1.9260. Min Act: -0.0000

Data Index: 1392754 (Python Code)

Max Activating Token Index: 370

Text #1

Max Range: 1.9260. Min Range: -1.9260

Max Act: 1.6750. Min Act: -0.0000

Data Index: 944723 (C4 (Web Text))

Max Activating Token Index: 265

Text #2

Max Range: 1.9260. Min Range: -1.9260

Max Act: 1.7138. Min Act: -0.0000

Data Index: 1228392 (C4 (Web Text))

Max Activating Token Index: 146

Text #3

Max Range: 1.9260. Min Range: -1.9260

Max Act: 1.7066. Min Act: -0.0000

Data Index: 493044 (C4 (Web Text))

Max Activating Token Index: 310

Text #4

Max Range: 1.9260. Min Range: -1.9260

Max Act: 1.8064. Min Act: -0.0000

Data Index: 316416 (C4 (Web Text))

Max Activating Token Index: 115

Text #5

Max Range: 1.9260. Min Range: -1.9260

Max Act: 1.7673. Min Act: -0.0000

Data Index: 1531386 (Python Code)

Max Activating Token Index: 25

Text #6

Max Range: 1.9260. Min Range: -1.9260

Max Act: 1.7308. Min Act: -0.0000

Data Index: 18585 (C4 (Web Text))

Max Activating Token Index: 115

Text #7

Max Range: 1.9260. Min Range: -1.9260

Max Act: 1.8137. Min Act: -0.0000

Data Index: 199186 (C4 (Web Text))

Max Activating Token Index: 150

Text #8

Max Range: 1.9260. Min Range: -1.9260

Max Act: 1.9187. Min Act: -0.0000

Data Index: 229343 (C4 (Web Text))

Max Activating Token Index: 314

Text #9

Max Range: 1.9260. Min Range: -1.9260

Max Act: 1.6853. Min Act: -0.0000

Data Index: 1438880 (Python Code)

Max Activating Token Index: 8

Text #10

Max Range: 1.9260. Min Range: -1.9260

Max Act: 1.5872. Min Act: -0.0000

Data Index: 1257111 (C4 (Web Text))

Max Activating Token Index: 381

Text #11

Max Range: 1.9260. Min Range: -1.9260

Max Act: 1.6786. Min Act: -0.0000

Data Index: 825965 (C4 (Web Text))

Max Activating Token Index: 450

Text #12

Max Range: 1.9260. Min Range: -1.9260

Max Act: 1.7598. Min Act: -0.0000

Data Index: 1498695 (Python Code)

Max Activating Token Index: 199

Text #13

Max Range: 1.9260. Min Range: -1.9260

Max Act: 1.7430. Min Act: -0.0000

Data Index: 1217027 (C4 (Web Text))

Max Activating Token Index: 757

Text #14

Max Range: 1.9260. Min Range: -1.9260

Max Act: 1.7130. Min Act: -0.0000

Data Index: 333281 (C4 (Web Text))

Max Activating Token Index: 875

Text #15

Max Range: 1.9260. Min Range: -1.9260

Max Act: 1.4293. Min Act: -0.0000

Data Index: 458702 (C4 (Web Text))

Max Activating Token Index: 299

Text #16

Max Range: 1.9260. Min Range: -1.9260

Max Act: 1.6987. Min Act: -0.0000

Data Index: 632573 (C4 (Web Text))

Max Activating Token Index: 220

Text #17

Max Range: 1.9260. Min Range: -1.9260

Max Act: 1.6987. Min Act: -0.0000

Data Index: 1365917 (Python Code)

Max Activating Token Index: 60

Text #18

Max Range: 1.9260. Min Range: -1.9260

Max Act: 1.6991. Min Act: -0.0000

Data Index: 709535 (C4 (Web Text))

Max Activating Token Index: 119

Text #19

Max Range: 1.9260. Min Range: -1.9260

Max Act: 1.6054. Min Act: -0.0000

Data Index: 837908 (C4 (Web Text))

Max Activating Token Index: 242