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

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

Neuron 1248 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2759. Min Range: -0.2759

Max Act: 0.2759. Min Act: -0.0000

Data Index: 112046 (C4 (Web Text))

Max Activating Token Index: 291

Text #1

Max Range: 0.2759. Min Range: -0.2759

Max Act: 0.2634. Min Act: -0.0001

Data Index: 354963 (C4 (Web Text))

Max Activating Token Index: 1014

Text #2

Max Range: 0.2759. Min Range: -0.2759

Max Act: 0.2680. Min Act: -0.0000

Data Index: 1116508 (C4 (Web Text))

Max Activating Token Index: 1019

Text #3

Max Range: 0.2759. Min Range: -0.2759

Max Act: 0.2536. Min Act: -0.0000

Data Index: 1356805 (C4 (Web Text))

Max Activating Token Index: 985

Text #4

Max Range: 0.2759. Min Range: -0.2759

Max Act: 0.2427. Min Act: -0.0000

Data Index: 255551 (C4 (Web Text))

Max Activating Token Index: 422

Text #5

Max Range: 0.2759. Min Range: -0.2759

Max Act: 0.2320. Min Act: -0.0000

Data Index: 871452 (C4 (Web Text))

Max Activating Token Index: 34

Text #6

Max Range: 0.2759. Min Range: -0.2759

Max Act: 0.2117. Min Act: -0.0000

Data Index: 433740 (C4 (Web Text))

Max Activating Token Index: 473

Text #7

Max Range: 0.2759. Min Range: -0.2759

Max Act: 0.2203. Min Act: -0.0000

Data Index: 1059494 (C4 (Web Text))

Max Activating Token Index: 74

Text #8

Max Range: 0.2759. Min Range: -0.2759

Max Act: 0.2329. Min Act: -0.0000

Data Index: 318508 (C4 (Web Text))

Max Activating Token Index: 709

Text #9

Max Range: 0.2759. Min Range: -0.2759

Max Act: 0.2053. Min Act: -0.0001

Data Index: 1632464 (Python Code)

Max Activating Token Index: 57

Text #10

Max Range: 0.2759. Min Range: -0.2759

Max Act: 0.2030. Min Act: -0.0000

Data Index: 896598 (C4 (Web Text))

Max Activating Token Index: 408

Text #11

Max Range: 0.2759. Min Range: -0.2759

Max Act: 0.2013. Min Act: -0.0001

Data Index: 202341 (C4 (Web Text))

Max Activating Token Index: 650

Text #12

Max Range: 0.2759. Min Range: -0.2759

Max Act: 0.1989. Min Act: -0.0001

Data Index: 1453830 (Python Code)

Max Activating Token Index: 58

Text #13

Max Range: 0.2759. Min Range: -0.2759

Max Act: 0.1857. Min Act: -0.0001

Data Index: 339040 (C4 (Web Text))

Max Activating Token Index: 598

Text #14

Max Range: 0.2759. Min Range: -0.2759

Max Act: 0.1851. Min Act: 0.0000

Data Index: 715123 (C4 (Web Text))

Max Activating Token Index: 846

Text #15

Max Range: 0.2759. Min Range: -0.2759

Max Act: 0.1839. Min Act: -0.0000

Data Index: 459600 (C4 (Web Text))

Max Activating Token Index: 26

Text #16

Max Range: 0.2759. Min Range: -0.2759

Max Act: 0.1806. Min Act: -0.0000

Data Index: 2168 (C4 (Web Text))

Max Activating Token Index: 433

Text #17

Max Range: 0.2759. Min Range: -0.2759

Max Act: 0.1929. Min Act: -0.0000

Data Index: 1202126 (C4 (Web Text))

Max Activating Token Index: 786

Text #18

Max Range: 0.2759. Min Range: -0.2759

Max Act: 0.1799. Min Act: -0.0000

Data Index: 1171603 (C4 (Web Text))

Max Activating Token Index: 169

Text #19

Max Range: 0.2759. Min Range: -0.2759

Max Act: 0.1820. Min Act: 0.0001

Data Index: 390154 (C4 (Web Text))

Max Activating Token Index: 29