Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 115 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.2066. Min Range: -0.2066

Max Act: 0.1984. Min Act: 0.0001

Data Index: 1411637 (Python Code)

Max Activating Token Index: 650

Text #1

Max Range: 0.2066. Min Range: -0.2066

Max Act: 0.2039. Min Act: 0.0000

Data Index: 1513868 (Python Code)

Max Activating Token Index: 546

Text #2

Max Range: 0.2066. Min Range: -0.2066

Max Act: 0.2066. Min Act: -0.0003

Data Index: 838577 (C4 (Web Text))

Max Activating Token Index: 741

Text #3

Max Range: 0.2066. Min Range: -0.2066

Max Act: 0.2032. Min Act: 0.0001

Data Index: 1398981 (Python Code)

Max Activating Token Index: 843

Text #4

Max Range: 0.2066. Min Range: -0.2066

Max Act: 0.1964. Min Act: -0.0002

Data Index: 1478479 (Python Code)

Max Activating Token Index: 980

Text #5

Max Range: 0.2066. Min Range: -0.2066

Max Act: 0.2002. Min Act: 0.0001

Data Index: 1511266 (Python Code)

Max Activating Token Index: 945

Text #6

Max Range: 0.2066. Min Range: -0.2066

Max Act: 0.1945. Min Act: -0.0000

Data Index: 1545199 (Python Code)

Max Activating Token Index: 511

Text #7

Max Range: 0.2066. Min Range: -0.2066

Max Act: 0.1955. Min Act: 0.0001

Data Index: 1422199 (Python Code)

Max Activating Token Index: 980

Text #8

Max Range: 0.2066. Min Range: -0.2066

Max Act: 0.1941. Min Act: 0.0001

Data Index: 1428729 (Python Code)

Max Activating Token Index: 892

Text #9

Max Range: 0.2066. Min Range: -0.2066

Max Act: 0.1884. Min Act: -0.0002

Data Index: 1462229 (Python Code)

Max Activating Token Index: 934

Text #10

Max Range: 0.2066. Min Range: -0.2066

Max Act: 0.1940. Min Act: 0.0001

Data Index: 1622617 (Python Code)

Max Activating Token Index: 931

Text #11

Max Range: 0.2066. Min Range: -0.2066

Max Act: 0.1850. Min Act: 0.0000

Data Index: 1473538 (Python Code)

Max Activating Token Index: 541

Text #12

Max Range: 0.2066. Min Range: -0.2066

Max Act: 0.1925. Min Act: -0.0001

Data Index: 1431704 (Python Code)

Max Activating Token Index: 845

Text #13

Max Range: 0.2066. Min Range: -0.2066

Max Act: 0.1851. Min Act: -0.0001

Data Index: 1444338 (Python Code)

Max Activating Token Index: 522

Text #14

Max Range: 0.2066. Min Range: -0.2066

Max Act: 0.1917. Min Act: -0.0002

Data Index: 1442562 (Python Code)

Max Activating Token Index: 688

Text #15

Max Range: 0.2066. Min Range: -0.2066

Max Act: 0.1869. Min Act: -0.0000

Data Index: 1378217 (Python Code)

Max Activating Token Index: 857

Text #16

Max Range: 0.2066. Min Range: -0.2066

Max Act: 0.1859. Min Act: -0.0001

Data Index: 1431274 (Python Code)

Max Activating Token Index: 572

Text #17

Max Range: 0.2066. Min Range: -0.2066

Max Act: 0.1866. Min Act: -0.0001

Data Index: 1363818 (Python Code)

Max Activating Token Index: 819

Text #18

Max Range: 0.2066. Min Range: -0.2066

Max Act: 0.1852. Min Act: 0.0004

Data Index: 1632190 (Python Code)

Max Activating Token Index: 330

Text #19

Max Range: 0.2066. Min Range: -0.2066

Max Act: 0.1854. Min Act: 0.0000

Data Index: 1644739 (Python Code)

Max Activating Token Index: 692