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

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

Neuron 3986 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: 0.8579. Min Range: -0.8579

Max Act: 0.8579. Min Act: -0.0000

Data Index: 381072 (C4 (Web Text))

Max Activating Token Index: 277

Text #1

Max Range: 0.8579. Min Range: -0.8579

Max Act: 0.7911. Min Act: -0.0000

Data Index: 1499107 (Python Code)

Max Activating Token Index: 395

Text #2

Max Range: 0.8579. Min Range: -0.8579

Max Act: 0.8122. Min Act: -0.0000

Data Index: 1408963 (Python Code)

Max Activating Token Index: 877

Text #3

Max Range: 0.8579. Min Range: -0.8579

Max Act: 0.7224. Min Act: -0.0000

Data Index: 1165268 (C4 (Web Text))

Max Activating Token Index: 897

Text #4

Max Range: 0.8579. Min Range: -0.8579

Max Act: 0.7073. Min Act: -0.0000

Data Index: 1442674 (Python Code)

Max Activating Token Index: 790

Text #5

Max Range: 0.8579. Min Range: -0.8579

Max Act: 0.6611. Min Act: -0.0000

Data Index: 916833 (C4 (Web Text))

Max Activating Token Index: 681

Text #6

Max Range: 0.8579. Min Range: -0.8579

Max Act: 0.6868. Min Act: -0.0000

Data Index: 1540152 (Python Code)

Max Activating Token Index: 972

Text #7

Max Range: 0.8579. Min Range: -0.8579

Max Act: 0.6835. Min Act: -0.0000

Data Index: 1631012 (Python Code)

Max Activating Token Index: 531

Text #8

Max Range: 0.8579. Min Range: -0.8579

Max Act: 0.6355. Min Act: -0.0000

Data Index: 1521197 (Python Code)

Max Activating Token Index: 972

Text #9

Max Range: 0.8579. Min Range: -0.8579

Max Act: 0.6910. Min Act: -0.0000

Data Index: 1634680 (Python Code)

Max Activating Token Index: 802

Text #10

Max Range: 0.8579. Min Range: -0.8579

Max Act: 0.6101. Min Act: -0.0000

Data Index: 1507548 (Python Code)

Max Activating Token Index: 910

Text #11

Max Range: 0.8579. Min Range: -0.8579

Max Act: 0.6771. Min Act: -0.0000

Data Index: 1524634 (Python Code)

Max Activating Token Index: 591

Text #12

Max Range: 0.8579. Min Range: -0.8579

Max Act: 0.6238. Min Act: -0.0000

Data Index: 1624247 (Python Code)

Max Activating Token Index: 675

Text #13

Max Range: 0.8579. Min Range: -0.8579

Max Act: 0.6834. Min Act: -0.0000

Data Index: 1480391 (Python Code)

Max Activating Token Index: 735

Text #14

Max Range: 0.8579. Min Range: -0.8579

Max Act: 0.6651. Min Act: -0.0000

Data Index: 1360634 (Python Code)

Max Activating Token Index: 424

Text #15

Max Range: 0.8579. Min Range: -0.8579

Max Act: 0.6436. Min Act: -0.0000

Data Index: 1417992 (Python Code)

Max Activating Token Index: 466

Text #16

Max Range: 0.8579. Min Range: -0.8579

Max Act: 0.6247. Min Act: -0.0000

Data Index: 1575448 (Python Code)

Max Activating Token Index: 843

Text #17

Max Range: 0.8579. Min Range: -0.8579

Max Act: 0.6187. Min Act: -0.0000

Data Index: 1374396 (Python Code)

Max Activating Token Index: 779

Text #18

Max Range: 0.8579. Min Range: -0.8579

Max Act: 0.6410. Min Act: -0.0000

Data Index: 755716 (C4 (Web Text))

Max Activating Token Index: 376

Text #19

Max Range: 0.8579. Min Range: -0.8579

Max Act: 0.6025. Min Act: -0.0000

Data Index: 1615151 (Python Code)

Max Activating Token Index: 846