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

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

Neuron 5212 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0316. Min Act: -0.0001

Data Index: 1622416 (Python Code)

Max Activating Token Index: 898

Text #1

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0349. Min Act: -0.0001

Data Index: 1399600 (Python Code)

Max Activating Token Index: 176

Text #2

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0387. Min Act: -0.0001

Data Index: 980766 (C4 (Web Text))

Max Activating Token Index: 213

Text #3

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0351. Min Act: -0.0001

Data Index: 1391229 (Python Code)

Max Activating Token Index: 1001

Text #4

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0331. Min Act: -0.0001

Data Index: 99593 (C4 (Web Text))

Max Activating Token Index: 9

Text #5

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0379. Min Act: -0.0001

Data Index: 1230974 (C4 (Web Text))

Max Activating Token Index: 1017

Text #6

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0312. Min Act: -0.0001

Data Index: 1565652 (Python Code)

Max Activating Token Index: 168

Text #7

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0356. Min Act: -0.0001

Data Index: 940636 (C4 (Web Text))

Max Activating Token Index: 717

Text #8

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0354. Min Act: -0.0001

Data Index: 917338 (C4 (Web Text))

Max Activating Token Index: 927

Text #9

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0296. Min Act: -0.0001

Data Index: 553744 (C4 (Web Text))

Max Activating Token Index: 600

Text #10

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0262. Min Act: -0.0001

Data Index: 1505555 (Python Code)

Max Activating Token Index: 389

Text #11

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0286. Min Act: -0.0001

Data Index: 930260 (C4 (Web Text))

Max Activating Token Index: 577

Text #12

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0295. Min Act: -0.0001

Data Index: 1564672 (Python Code)

Max Activating Token Index: 100

Text #13

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0268. Min Act: -0.0001

Data Index: 594304 (C4 (Web Text))

Max Activating Token Index: 563

Text #14

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0251. Min Act: -0.0001

Data Index: 259699 (C4 (Web Text))

Max Activating Token Index: 185

Text #15

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0259. Min Act: -0.0001

Data Index: 517738 (C4 (Web Text))

Max Activating Token Index: 10

Text #16

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0249. Min Act: -0.0001

Data Index: 1457126 (Python Code)

Max Activating Token Index: 1015

Text #17

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0250. Min Act: -0.0001

Data Index: 1532652 (Python Code)

Max Activating Token Index: 574

Text #18

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0272. Min Act: -0.0001

Data Index: 238164 (C4 (Web Text))

Max Activating Token Index: 283

Text #19

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0224. Min Act: -0.0001

Data Index: 24262 (C4 (Web Text))

Max Activating Token Index: 241