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

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

Neuron 2107 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6217. Min Range: -0.6217

Max Act: 0.6217. Min Act: -0.0000

Data Index: 468064 (C4 (Web Text))

Max Activating Token Index: 567

Text #1

Max Range: 0.6217. Min Range: -0.6217

Max Act: 0.5251. Min Act: -0.0000

Data Index: 1570209 (Python Code)

Max Activating Token Index: 258

Text #2

Max Range: 0.6217. Min Range: -0.6217

Max Act: 0.5026. Min Act: -0.0000

Data Index: 1540110 (Python Code)

Max Activating Token Index: 113

Text #3

Max Range: 0.6217. Min Range: -0.6217

Max Act: 0.4978. Min Act: -0.0000

Data Index: 1515547 (Python Code)

Max Activating Token Index: 305

Text #4

Max Range: 0.6217. Min Range: -0.6217

Max Act: 0.5092. Min Act: -0.0000

Data Index: 73956 (C4 (Web Text))

Max Activating Token Index: 417

Text #5

Max Range: 0.6217. Min Range: -0.6217

Max Act: 0.4797. Min Act: -0.0000

Data Index: 1016860 (C4 (Web Text))

Max Activating Token Index: 452

Text #6

Max Range: 0.6217. Min Range: -0.6217

Max Act: 0.4972. Min Act: -0.0000

Data Index: 1437792 (Python Code)

Max Activating Token Index: 163

Text #7

Max Range: 0.6217. Min Range: -0.6217

Max Act: 0.5200. Min Act: -0.0000

Data Index: 1442538 (Python Code)

Max Activating Token Index: 320

Text #8

Max Range: 0.6217. Min Range: -0.6217

Max Act: 0.4782. Min Act: -0.0000

Data Index: 1440502 (Python Code)

Max Activating Token Index: 118

Text #9

Max Range: 0.6217. Min Range: -0.6217

Max Act: 0.4567. Min Act: -0.0000

Data Index: 1627867 (Python Code)

Max Activating Token Index: 159

Text #10

Max Range: 0.6217. Min Range: -0.6217

Max Act: 0.4582. Min Act: -0.0000

Data Index: 186675 (C4 (Web Text))

Max Activating Token Index: 882

Text #11

Max Range: 0.6217. Min Range: -0.6217

Max Act: 0.4267. Min Act: -0.0000

Data Index: 527664 (C4 (Web Text))

Max Activating Token Index: 806

Text #12

Max Range: 0.6217. Min Range: -0.6217

Max Act: 0.4411. Min Act: -0.0000

Data Index: 1089270 (C4 (Web Text))

Max Activating Token Index: 963

Text #13

Max Range: 0.6217. Min Range: -0.6217

Max Act: 0.4006. Min Act: -0.0000

Data Index: 96996 (C4 (Web Text))

Max Activating Token Index: 989

Text #14

Max Range: 0.6217. Min Range: -0.6217

Max Act: 0.4096. Min Act: -0.0000

Data Index: 1246795 (C4 (Web Text))

Max Activating Token Index: 1003

Text #15

Max Range: 0.6217. Min Range: -0.6217

Max Act: 0.4216. Min Act: -0.0000

Data Index: 1365518 (Python Code)

Max Activating Token Index: 475

Text #16

Max Range: 0.6217. Min Range: -0.6217

Max Act: 0.4102. Min Act: -0.0000

Data Index: 676305 (C4 (Web Text))

Max Activating Token Index: 93

Text #17

Max Range: 0.6217. Min Range: -0.6217

Max Act: 0.4268. Min Act: -0.0000

Data Index: 1409178 (Python Code)

Max Activating Token Index: 384

Text #18

Max Range: 0.6217. Min Range: -0.6217

Max Act: 0.3976. Min Act: -0.0000

Data Index: 1431639 (Python Code)

Max Activating Token Index: 265

Text #19

Max Range: 0.6217. Min Range: -0.6217

Max Act: 0.4240. Min Act: -0.0000

Data Index: 868517 (C4 (Web Text))

Max Activating Token Index: 265