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

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

Neuron 5912 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2777. Min Range: -0.2777

Max Act: 0.2777. Min Act: -0.0000

Data Index: 1296614 (C4 (Web Text))

Max Activating Token Index: 919

Text #1

Max Range: 0.2777. Min Range: -0.2777

Max Act: 0.2186. Min Act: -0.0000

Data Index: 1609316 (Python Code)

Max Activating Token Index: 327

Text #2

Max Range: 0.2777. Min Range: -0.2777

Max Act: 0.2091. Min Act: -0.0000

Data Index: 989278 (C4 (Web Text))

Max Activating Token Index: 701

Text #3

Max Range: 0.2777. Min Range: -0.2777

Max Act: 0.1933. Min Act: -0.0000

Data Index: 1301778 (C4 (Web Text))

Max Activating Token Index: 867

Text #4

Max Range: 0.2777. Min Range: -0.2777

Max Act: 0.2068. Min Act: -0.0000

Data Index: 1438974 (Python Code)

Max Activating Token Index: 405

Text #5

Max Range: 0.2777. Min Range: -0.2777

Max Act: 0.1834. Min Act: -0.0000

Data Index: 449884 (C4 (Web Text))

Max Activating Token Index: 855

Text #6

Max Range: 0.2777. Min Range: -0.2777

Max Act: 0.2024. Min Act: -0.0000

Data Index: 1544006 (Python Code)

Max Activating Token Index: 330

Text #7

Max Range: 0.2777. Min Range: -0.2777

Max Act: 0.1996. Min Act: -0.0000

Data Index: 1041177 (C4 (Web Text))

Max Activating Token Index: 836

Text #8

Max Range: 0.2777. Min Range: -0.2777

Max Act: 0.2052. Min Act: -0.0000

Data Index: 1538126 (Python Code)

Max Activating Token Index: 86

Text #9

Max Range: 0.2777. Min Range: -0.2777

Max Act: 0.2057. Min Act: -0.0000

Data Index: 1625204 (Python Code)

Max Activating Token Index: 748

Text #10

Max Range: 0.2777. Min Range: -0.2777

Max Act: 0.2055. Min Act: -0.0000

Data Index: 1458223 (Python Code)

Max Activating Token Index: 58

Text #11

Max Range: 0.2777. Min Range: -0.2777

Max Act: 0.2179. Min Act: -0.0000

Data Index: 828068 (C4 (Web Text))

Max Activating Token Index: 776

Text #12

Max Range: 0.2777. Min Range: -0.2777

Max Act: 0.1950. Min Act: -0.0000

Data Index: 1424917 (Python Code)

Max Activating Token Index: 856

Text #13

Max Range: 0.2777. Min Range: -0.2777

Max Act: 0.1847. Min Act: -0.0000

Data Index: 1427862 (Python Code)

Max Activating Token Index: 603

Text #14

Max Range: 0.2777. Min Range: -0.2777

Max Act: 0.1869. Min Act: -0.0000

Data Index: 1458597 (Python Code)

Max Activating Token Index: 460

Text #15

Max Range: 0.2777. Min Range: -0.2777

Max Act: 0.1830. Min Act: -0.0000

Data Index: 1314683 (C4 (Web Text))

Max Activating Token Index: 256

Text #16

Max Range: 0.2777. Min Range: -0.2777

Max Act: 0.1792. Min Act: -0.0000

Data Index: 1646999 (Python Code)

Max Activating Token Index: 402

Text #17

Max Range: 0.2777. Min Range: -0.2777

Max Act: 0.1906. Min Act: -0.0000

Data Index: 1377410 (Python Code)

Max Activating Token Index: 521

Text #18

Max Range: 0.2777. Min Range: -0.2777

Max Act: 0.1837. Min Act: -0.0000

Data Index: 1578882 (Python Code)

Max Activating Token Index: 461

Text #19

Max Range: 0.2777. Min Range: -0.2777

Max Act: 0.1903. Min Act: -0.0000

Data Index: 1507271 (Python Code)

Max Activating Token Index: 905