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

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

Neuron 403 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2363. Min Range: -0.2363

Max Act: 0.2363. Min Act: -0.0000

Data Index: 533897 (C4 (Web Text))

Max Activating Token Index: 193

Text #1

Max Range: 0.2363. Min Range: -0.2363

Max Act: 0.2119. Min Act: -0.0001

Data Index: 862584 (C4 (Web Text))

Max Activating Token Index: 531

Text #2

Max Range: 0.2363. Min Range: -0.2363

Max Act: 0.2182. Min Act: -0.0000

Data Index: 167551 (C4 (Web Text))

Max Activating Token Index: 174

Text #3

Max Range: 0.2363. Min Range: -0.2363

Max Act: 0.1999. Min Act: -0.0001

Data Index: 227939 (C4 (Web Text))

Max Activating Token Index: 40

Text #4

Max Range: 0.2363. Min Range: -0.2363

Max Act: 0.2040. Min Act: -0.0000

Data Index: 1235458 (C4 (Web Text))

Max Activating Token Index: 705

Text #5

Max Range: 0.2363. Min Range: -0.2363

Max Act: 0.1962. Min Act: -0.0001

Data Index: 664198 (C4 (Web Text))

Max Activating Token Index: 700

Text #6

Max Range: 0.2363. Min Range: -0.2363

Max Act: 0.1952. Min Act: -0.0001

Data Index: 1153857 (C4 (Web Text))

Max Activating Token Index: 673

Text #7

Max Range: 0.2363. Min Range: -0.2363

Max Act: 0.1894. Min Act: -0.0001

Data Index: 709626 (C4 (Web Text))

Max Activating Token Index: 960

Text #8

Max Range: 0.2363. Min Range: -0.2363

Max Act: 0.1797. Min Act: -0.0001

Data Index: 980209 (C4 (Web Text))

Max Activating Token Index: 737

Text #9

Max Range: 0.2363. Min Range: -0.2363

Max Act: 0.1889. Min Act: -0.0001

Data Index: 656138 (C4 (Web Text))

Max Activating Token Index: 790

Text #10

Max Range: 0.2363. Min Range: -0.2363

Max Act: 0.1870. Min Act: -0.0001

Data Index: 686830 (C4 (Web Text))

Max Activating Token Index: 987

Text #11

Max Range: 0.2363. Min Range: -0.2363

Max Act: 0.1827. Min Act: -0.0000

Data Index: 526342 (C4 (Web Text))

Max Activating Token Index: 549

Text #12

Max Range: 0.2363. Min Range: -0.2363

Max Act: 0.1853. Min Act: -0.0001

Data Index: 204600 (C4 (Web Text))

Max Activating Token Index: 662

Text #13

Max Range: 0.2363. Min Range: -0.2363

Max Act: 0.1910. Min Act: -0.0001

Data Index: 901313 (C4 (Web Text))

Max Activating Token Index: 467

Text #14

Max Range: 0.2363. Min Range: -0.2363

Max Act: 0.1825. Min Act: -0.0000

Data Index: 1006167 (C4 (Web Text))

Max Activating Token Index: 668

Text #15

Max Range: 0.2363. Min Range: -0.2363

Max Act: 0.1832. Min Act: -0.0000

Data Index: 886465 (C4 (Web Text))

Max Activating Token Index: 977

Text #16

Max Range: 0.2363. Min Range: -0.2363

Max Act: 0.1826. Min Act: -0.0001

Data Index: 48092 (C4 (Web Text))

Max Activating Token Index: 432

Text #17

Max Range: 0.2363. Min Range: -0.2363

Max Act: 0.1830. Min Act: -0.0000

Data Index: 844528 (C4 (Web Text))

Max Activating Token Index: 913

Text #18

Max Range: 0.2363. Min Range: -0.2363

Max Act: 0.1868. Min Act: -0.0001

Data Index: 798996 (C4 (Web Text))

Max Activating Token Index: 610

Text #19

Max Range: 0.2363. Min Range: -0.2363

Max Act: 0.1794. Min Act: -0.0001

Data Index: 911588 (C4 (Web Text))

Max Activating Token Index: 873