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

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

Neuron 2860 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.2218. Min Act: -0.0000

Data Index: 993444 (C4 (Web Text))

Max Activating Token Index: 963

Text #1

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.2107. Min Act: -0.0000

Data Index: 1408323 (Python Code)

Max Activating Token Index: 569

Text #2

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.2208. Min Act: -0.0000

Data Index: 924105 (C4 (Web Text))

Max Activating Token Index: 931

Text #3

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.2202. Min Act: -0.0000

Data Index: 576339 (C4 (Web Text))

Max Activating Token Index: 89

Text #4

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.2352. Min Act: -0.0000

Data Index: 1624715 (Python Code)

Max Activating Token Index: 803

Text #5

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.2057. Min Act: -0.0000

Data Index: 1505821 (Python Code)

Max Activating Token Index: 474

Text #6

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.1988. Min Act: -0.0000

Data Index: 339368 (C4 (Web Text))

Max Activating Token Index: 155

Text #7

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.1992. Min Act: -0.0000

Data Index: 1656589 (Python Code)

Max Activating Token Index: 207

Text #8

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.2056. Min Act: -0.0000

Data Index: 1462840 (Python Code)

Max Activating Token Index: 730

Text #9

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.1887. Min Act: -0.0000

Data Index: 1623575 (Python Code)

Max Activating Token Index: 55

Text #10

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.1876. Min Act: -0.0000

Data Index: 1482831 (Python Code)

Max Activating Token Index: 756

Text #11

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.1831. Min Act: -0.0000

Data Index: 692096 (C4 (Web Text))

Max Activating Token Index: 557

Text #12

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.1794. Min Act: -0.0000

Data Index: 1384713 (Python Code)

Max Activating Token Index: 958

Text #13

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.1839. Min Act: -0.0000

Data Index: 1503988 (Python Code)

Max Activating Token Index: 657

Text #14

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.1587. Min Act: -0.0000

Data Index: 131283 (C4 (Web Text))

Max Activating Token Index: 568

Text #15

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.1914. Min Act: -0.0000

Data Index: 1390479 (Python Code)

Max Activating Token Index: 917

Text #16

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.1659. Min Act: -0.0000

Data Index: 1536587 (Python Code)

Max Activating Token Index: 353

Text #17

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.1674. Min Act: -0.0000

Data Index: 878702 (C4 (Web Text))

Max Activating Token Index: 647

Text #18

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.1713. Min Act: -0.0000

Data Index: 696656 (C4 (Web Text))

Max Activating Token Index: 1001

Text #19

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.1663. Min Act: -0.0000

Data Index: 1166014 (C4 (Web Text))

Max Activating Token Index: 134