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

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

Neuron 1992 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2404. Min Range: -0.2404

Max Act: 0.2404. Min Act: -0.0000

Data Index: 134387 (C4 (Web Text))

Max Activating Token Index: 722

Text #1

Max Range: 0.2404. Min Range: -0.2404

Max Act: 0.2279. Min Act: -0.0000

Data Index: 1062803 (C4 (Web Text))

Max Activating Token Index: 401

Text #2

Max Range: 0.2404. Min Range: -0.2404

Max Act: 0.2182. Min Act: -0.0000

Data Index: 860607 (C4 (Web Text))

Max Activating Token Index: 601

Text #3

Max Range: 0.2404. Min Range: -0.2404

Max Act: 0.2210. Min Act: -0.0000

Data Index: 246997 (C4 (Web Text))

Max Activating Token Index: 561

Text #4

Max Range: 0.2404. Min Range: -0.2404

Max Act: 0.1864. Min Act: -0.0000

Data Index: 1344870 (C4 (Web Text))

Max Activating Token Index: 739

Text #5

Max Range: 0.2404. Min Range: -0.2404

Max Act: 0.1994. Min Act: -0.0000

Data Index: 50312 (C4 (Web Text))

Max Activating Token Index: 614

Text #6

Max Range: 0.2404. Min Range: -0.2404

Max Act: 0.1770. Min Act: -0.0000

Data Index: 1122951 (C4 (Web Text))

Max Activating Token Index: 280

Text #7

Max Range: 0.2404. Min Range: -0.2404

Max Act: 0.1884. Min Act: -0.0000

Data Index: 1391001 (Python Code)

Max Activating Token Index: 112

Text #8

Max Range: 0.2404. Min Range: -0.2404

Max Act: 0.2084. Min Act: -0.0000

Data Index: 1170660 (C4 (Web Text))

Max Activating Token Index: 315

Text #9

Max Range: 0.2404. Min Range: -0.2404

Max Act: 0.1705. Min Act: -0.0000

Data Index: 163074 (C4 (Web Text))

Max Activating Token Index: 401

Text #10

Max Range: 0.2404. Min Range: -0.2404

Max Act: 0.1814. Min Act: -0.0000

Data Index: 1226364 (C4 (Web Text))

Max Activating Token Index: 667

Text #11

Max Range: 0.2404. Min Range: -0.2404

Max Act: 0.1707. Min Act: -0.0000

Data Index: 537054 (C4 (Web Text))

Max Activating Token Index: 524

Text #12

Max Range: 0.2404. Min Range: -0.2404

Max Act: 0.1702. Min Act: -0.0000

Data Index: 1224496 (C4 (Web Text))

Max Activating Token Index: 596

Text #13

Max Range: 0.2404. Min Range: -0.2404

Max Act: 0.1820. Min Act: -0.0000

Data Index: 839994 (C4 (Web Text))

Max Activating Token Index: 168

Text #14

Max Range: 0.2404. Min Range: -0.2404

Max Act: 0.1714. Min Act: -0.0000

Data Index: 9336 (C4 (Web Text))

Max Activating Token Index: 623

Text #15

Max Range: 0.2404. Min Range: -0.2404

Max Act: 0.1724. Min Act: -0.0000

Data Index: 37860 (C4 (Web Text))

Max Activating Token Index: 821

Text #16

Max Range: 0.2404. Min Range: -0.2404

Max Act: 0.1728. Min Act: -0.0000

Data Index: 427312 (C4 (Web Text))

Max Activating Token Index: 648

Text #17

Max Range: 0.2404. Min Range: -0.2404

Max Act: 0.1519. Min Act: -0.0000

Data Index: 336055 (C4 (Web Text))

Max Activating Token Index: 915

Text #18

Max Range: 0.2404. Min Range: -0.2404

Max Act: 0.1769. Min Act: -0.0000

Data Index: 57075 (C4 (Web Text))

Max Activating Token Index: 448

Text #19

Max Range: 0.2404. Min Range: -0.2404

Max Act: 0.1612. Min Act: -0.0000

Data Index: 1042154 (C4 (Web Text))

Max Activating Token Index: 997