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

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

Neuron 3092 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.8010. Min Range: -0.8010

Max Act: 0.8010. Min Act: -0.0000

Data Index: 1270011 (C4 (Web Text))

Max Activating Token Index: 82

Text #1

Max Range: 0.8010. Min Range: -0.8010

Max Act: 0.6158. Min Act: -0.0000

Data Index: 131760 (C4 (Web Text))

Max Activating Token Index: 233

Text #2

Max Range: 0.8010. Min Range: -0.8010

Max Act: 0.5863. Min Act: -0.0000

Data Index: 1631897 (Python Code)

Max Activating Token Index: 1021

Text #3

Max Range: 0.8010. Min Range: -0.8010

Max Act: 0.5018. Min Act: -0.0000

Data Index: 995619 (C4 (Web Text))

Max Activating Token Index: 179

Text #4

Max Range: 0.8010. Min Range: -0.8010

Max Act: 0.5080. Min Act: -0.0000

Data Index: 594093 (C4 (Web Text))

Max Activating Token Index: 795

Text #5

Max Range: 0.8010. Min Range: -0.8010

Max Act: 0.5252. Min Act: -0.0000

Data Index: 1546514 (Python Code)

Max Activating Token Index: 98

Text #6

Max Range: 0.8010. Min Range: -0.8010

Max Act: 0.5060. Min Act: -0.0000

Data Index: 1635720 (Python Code)

Max Activating Token Index: 221

Text #7

Max Range: 0.8010. Min Range: -0.8010

Max Act: 0.5174. Min Act: -0.0000

Data Index: 158354 (C4 (Web Text))

Max Activating Token Index: 263

Text #8

Max Range: 0.8010. Min Range: -0.8010

Max Act: 0.5168. Min Act: -0.0000

Data Index: 308222 (C4 (Web Text))

Max Activating Token Index: 42

Text #9

Max Range: 0.8010. Min Range: -0.8010

Max Act: 0.5119. Min Act: -0.0000

Data Index: 1360456 (Python Code)

Max Activating Token Index: 732

Text #10

Max Range: 0.8010. Min Range: -0.8010

Max Act: 0.5191. Min Act: -0.0000

Data Index: 14842 (C4 (Web Text))

Max Activating Token Index: 686

Text #11

Max Range: 0.8010. Min Range: -0.8010

Max Act: 0.4832. Min Act: -0.0000

Data Index: 1524715 (Python Code)

Max Activating Token Index: 557

Text #12

Max Range: 0.8010. Min Range: -0.8010

Max Act: 0.4813. Min Act: -0.0000

Data Index: 1427548 (Python Code)

Max Activating Token Index: 609

Text #13

Max Range: 0.8010. Min Range: -0.8010

Max Act: 0.4714. Min Act: -0.0000

Data Index: 1362171 (Python Code)

Max Activating Token Index: 343

Text #14

Max Range: 0.8010. Min Range: -0.8010

Max Act: 0.5139. Min Act: -0.0000

Data Index: 568106 (C4 (Web Text))

Max Activating Token Index: 217

Text #15

Max Range: 0.8010. Min Range: -0.8010

Max Act: 0.4616. Min Act: -0.0000

Data Index: 1504370 (Python Code)

Max Activating Token Index: 510

Text #16

Max Range: 0.8010. Min Range: -0.8010

Max Act: 0.4762. Min Act: -0.0000

Data Index: 1356960 (C4 (Web Text))

Max Activating Token Index: 124

Text #17

Max Range: 0.8010. Min Range: -0.8010

Max Act: 0.4433. Min Act: -0.0000

Data Index: 342434 (C4 (Web Text))

Max Activating Token Index: 305

Text #18

Max Range: 0.8010. Min Range: -0.8010

Max Act: 0.4878. Min Act: -0.0000

Data Index: 1445088 (Python Code)

Max Activating Token Index: 1018

Text #19

Max Range: 0.8010. Min Range: -0.8010

Max Act: 0.4313. Min Act: -0.0000

Data Index: 356749 (C4 (Web Text))

Max Activating Token Index: 757