Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3707 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.2843. Min Range: -0.2843

Max Act: 0.2843. Min Act: -0.0000

Data Index: 1598464 (Python Code)

Max Activating Token Index: 779

Text #1

Max Range: 0.2843. Min Range: -0.2843

Max Act: 0.2542. Min Act: -0.0000

Data Index: 1558011 (Python Code)

Max Activating Token Index: 102

Text #2

Max Range: 0.2843. Min Range: -0.2843

Max Act: 0.2592. Min Act: -0.0000

Data Index: 1613617 (Python Code)

Max Activating Token Index: 836

Text #3

Max Range: 0.2843. Min Range: -0.2843

Max Act: 0.2179. Min Act: -0.0000

Data Index: 1505587 (Python Code)

Max Activating Token Index: 747

Text #4

Max Range: 0.2843. Min Range: -0.2843

Max Act: 0.2313. Min Act: -0.0000

Data Index: 1432742 (Python Code)

Max Activating Token Index: 438

Text #5

Max Range: 0.2843. Min Range: -0.2843

Max Act: 0.2122. Min Act: -0.0000

Data Index: 1391481 (Python Code)

Max Activating Token Index: 385

Text #6

Max Range: 0.2843. Min Range: -0.2843

Max Act: 0.2343. Min Act: -0.0000

Data Index: 1562630 (Python Code)

Max Activating Token Index: 681

Text #7

Max Range: 0.2843. Min Range: -0.2843

Max Act: 0.2225. Min Act: -0.0000

Data Index: 1529447 (Python Code)

Max Activating Token Index: 916

Text #8

Max Range: 0.2843. Min Range: -0.2843

Max Act: 0.2138. Min Act: -0.0000

Data Index: 1484174 (Python Code)

Max Activating Token Index: 73

Text #9

Max Range: 0.2843. Min Range: -0.2843

Max Act: 0.1927. Min Act: -0.0000

Data Index: 1555898 (Python Code)

Max Activating Token Index: 926

Text #10

Max Range: 0.2843. Min Range: -0.2843

Max Act: 0.2082. Min Act: -0.0000

Data Index: 1639671 (Python Code)

Max Activating Token Index: 201

Text #11

Max Range: 0.2843. Min Range: -0.2843

Max Act: 0.2026. Min Act: -0.0000

Data Index: 1651729 (Python Code)

Max Activating Token Index: 484

Text #12

Max Range: 0.2843. Min Range: -0.2843

Max Act: 0.2091. Min Act: -0.0000

Data Index: 1605887 (Python Code)

Max Activating Token Index: 710

Text #13

Max Range: 0.2843. Min Range: -0.2843

Max Act: 0.1940. Min Act: -0.0000

Data Index: 1508727 (Python Code)

Max Activating Token Index: 423

Text #14

Max Range: 0.2843. Min Range: -0.2843

Max Act: 0.2075. Min Act: -0.0000

Data Index: 1536776 (Python Code)

Max Activating Token Index: 907

Text #15

Max Range: 0.2843. Min Range: -0.2843

Max Act: 0.1937. Min Act: -0.0000

Data Index: 1387545 (Python Code)

Max Activating Token Index: 658

Text #16

Max Range: 0.2843. Min Range: -0.2843

Max Act: 0.1841. Min Act: -0.0000

Data Index: 1478738 (Python Code)

Max Activating Token Index: 794

Text #17

Max Range: 0.2843. Min Range: -0.2843

Max Act: 0.1919. Min Act: -0.0000

Data Index: 1614040 (Python Code)

Max Activating Token Index: 677

Text #18

Max Range: 0.2843. Min Range: -0.2843

Max Act: 0.2174. Min Act: -0.0000

Data Index: 1541739 (Python Code)

Max Activating Token Index: 124

Text #19

Max Range: 0.2843. Min Range: -0.2843

Max Act: 0.1938. Min Act: -0.0000

Data Index: 1396762 (Python Code)

Max Activating Token Index: 1000