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

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

Neuron 1137 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9326. Min Range: -1.9326

Max Act: 1.9326. Min Act: -0.0000

Data Index: 317580 (C4 (Web Text))

Max Activating Token Index: 392

Text #1

Max Range: 1.9326. Min Range: -1.9326

Max Act: 1.7887. Min Act: -0.0000

Data Index: 1569866 (Python Code)

Max Activating Token Index: 497

Text #2

Max Range: 1.9326. Min Range: -1.9326

Max Act: 1.7960. Min Act: -0.0000

Data Index: 1584610 (Python Code)

Max Activating Token Index: 382

Text #3

Max Range: 1.9326. Min Range: -1.9326

Max Act: 1.7969. Min Act: -0.0000

Data Index: 1506995 (Python Code)

Max Activating Token Index: 194

Text #4

Max Range: 1.9326. Min Range: -1.9326

Max Act: 1.6811. Min Act: -0.0000

Data Index: 1432256 (Python Code)

Max Activating Token Index: 688

Text #5

Max Range: 1.9326. Min Range: -1.9326

Max Act: 1.7237. Min Act: -0.0000

Data Index: 1565199 (Python Code)

Max Activating Token Index: 555

Text #6

Max Range: 1.9326. Min Range: -1.9326

Max Act: 1.7486. Min Act: -0.0000

Data Index: 1384447 (Python Code)

Max Activating Token Index: 975

Text #7

Max Range: 1.9326. Min Range: -1.9326

Max Act: 1.6246. Min Act: -0.0000

Data Index: 1524257 (Python Code)

Max Activating Token Index: 600

Text #8

Max Range: 1.9326. Min Range: -1.9326

Max Act: 1.6762. Min Act: -0.0000

Data Index: 1501825 (Python Code)

Max Activating Token Index: 796

Text #9

Max Range: 1.9326. Min Range: -1.9326

Max Act: 1.6712. Min Act: -0.0000

Data Index: 1642280 (Python Code)

Max Activating Token Index: 890

Text #10

Max Range: 1.9326. Min Range: -1.9326

Max Act: 1.6552. Min Act: -0.0000

Data Index: 1556704 (Python Code)

Max Activating Token Index: 730

Text #11

Max Range: 1.9326. Min Range: -1.9326

Max Act: 1.7342. Min Act: -0.0000

Data Index: 754233 (C4 (Web Text))

Max Activating Token Index: 920

Text #12

Max Range: 1.9326. Min Range: -1.9326

Max Act: 1.5480. Min Act: -0.0000

Data Index: 1588073 (Python Code)

Max Activating Token Index: 472

Text #13

Max Range: 1.9326. Min Range: -1.9326

Max Act: 1.4798. Min Act: -0.0000

Data Index: 1497090 (Python Code)

Max Activating Token Index: 365

Text #14

Max Range: 1.9326. Min Range: -1.9326

Max Act: 1.4775. Min Act: -0.0000

Data Index: 1491288 (Python Code)

Max Activating Token Index: 225

Text #15

Max Range: 1.9326. Min Range: -1.9326

Max Act: 1.5525. Min Act: -0.0000

Data Index: 1480815 (Python Code)

Max Activating Token Index: 139

Text #16

Max Range: 1.9326. Min Range: -1.9326

Max Act: 1.4240. Min Act: -0.0000

Data Index: 1605367 (Python Code)

Max Activating Token Index: 764

Text #17

Max Range: 1.9326. Min Range: -1.9326

Max Act: 1.3462. Min Act: -0.0000

Data Index: 1384542 (Python Code)

Max Activating Token Index: 151

Text #18

Max Range: 1.9326. Min Range: -1.9326

Max Act: 1.4144. Min Act: -0.0000

Data Index: 1629746 (Python Code)

Max Activating Token Index: 544

Text #19

Max Range: 1.9326. Min Range: -1.9326

Max Act: 1.4599. Min Act: -0.0000

Data Index: 1466041 (Python Code)

Max Activating Token Index: 323