Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1237 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.2269. Min Range: -1.2269

Max Act: 1.2269. Min Act: -0.0001

Data Index: 183538 (C4 (Web Text))

Max Activating Token Index: 668

Text #1

Max Range: 1.2269. Min Range: -1.2269

Max Act: 0.9781. Min Act: -0.0001

Data Index: 1449178 (Python Code)

Max Activating Token Index: 759

Text #2

Max Range: 1.2269. Min Range: -1.2269

Max Act: 1.0682. Min Act: -0.0001

Data Index: 191851 (C4 (Web Text))

Max Activating Token Index: 902

Text #3

Max Range: 1.2269. Min Range: -1.2269

Max Act: 1.0089. Min Act: -0.0001

Data Index: 1146137 (C4 (Web Text))

Max Activating Token Index: 624

Text #4

Max Range: 1.2269. Min Range: -1.2269

Max Act: 0.9851. Min Act: -0.0001

Data Index: 1453384 (Python Code)

Max Activating Token Index: 457

Text #5

Max Range: 1.2269. Min Range: -1.2269

Max Act: 0.8996. Min Act: -0.0001

Data Index: 588880 (C4 (Web Text))

Max Activating Token Index: 18

Text #6

Max Range: 1.2269. Min Range: -1.2269

Max Act: 0.8670. Min Act: -0.0001

Data Index: 1404289 (Python Code)

Max Activating Token Index: 587

Text #7

Max Range: 1.2269. Min Range: -1.2269

Max Act: 0.8631. Min Act: -0.0001

Data Index: 1117471 (C4 (Web Text))

Max Activating Token Index: 656

Text #8

Max Range: 1.2269. Min Range: -1.2269

Max Act: 0.9168. Min Act: -0.0001

Data Index: 1310785 (C4 (Web Text))

Max Activating Token Index: 387

Text #9

Max Range: 1.2269. Min Range: -1.2269

Max Act: 0.8503. Min Act: -0.0001

Data Index: 1576878 (Python Code)

Max Activating Token Index: 867

Text #10

Max Range: 1.2269. Min Range: -1.2269

Max Act: 0.8856. Min Act: -0.0001

Data Index: 623132 (C4 (Web Text))

Max Activating Token Index: 796

Text #11

Max Range: 1.2269. Min Range: -1.2269

Max Act: 0.8831. Min Act: -0.0001

Data Index: 18793 (C4 (Web Text))

Max Activating Token Index: 884

Text #12

Max Range: 1.2269. Min Range: -1.2269

Max Act: 0.8540. Min Act: -0.0001

Data Index: 477993 (C4 (Web Text))

Max Activating Token Index: 55

Text #13

Max Range: 1.2269. Min Range: -1.2269

Max Act: 0.9052. Min Act: -0.0001

Data Index: 930158 (C4 (Web Text))

Max Activating Token Index: 88

Text #14

Max Range: 1.2269. Min Range: -1.2269

Max Act: 0.9268. Min Act: -0.0001

Data Index: 853379 (C4 (Web Text))

Max Activating Token Index: 857

Text #15

Max Range: 1.2269. Min Range: -1.2269

Max Act: 0.8910. Min Act: -0.0001

Data Index: 1456331 (Python Code)

Max Activating Token Index: 661

Text #16

Max Range: 1.2269. Min Range: -1.2269

Max Act: 0.8625. Min Act: -0.0001

Data Index: 234821 (C4 (Web Text))

Max Activating Token Index: 691

Text #17

Max Range: 1.2269. Min Range: -1.2269

Max Act: 0.8557. Min Act: -0.0001

Data Index: 83524 (C4 (Web Text))

Max Activating Token Index: 262

Text #18

Max Range: 1.2269. Min Range: -1.2269

Max Act: 0.8426. Min Act: -0.0001

Data Index: 1228641 (C4 (Web Text))

Max Activating Token Index: 581

Text #19

Max Range: 1.2269. Min Range: -1.2269

Max Act: 0.7882. Min Act: -0.0001

Data Index: 1593411 (Python Code)

Max Activating Token Index: 781