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

Dataset: The Pile

Neuron 2285 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.2369. Min Act: -0.0000

Data Index: 1883834 (The Pile)

Max Activating Token Index: 890

Text #1

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.2182. Min Act: -0.0000

Data Index: 353105 (The Pile)

Max Activating Token Index: 858

Text #2

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.2258. Min Act: -0.0000

Data Index: 1532185 (The Pile)

Max Activating Token Index: 658

Text #3

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.2540. Min Act: -0.0000

Data Index: 1926100 (The Pile)

Max Activating Token Index: 951

Text #4

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.2048. Min Act: -0.0000

Data Index: 1024530 (The Pile)

Max Activating Token Index: 640

Text #5

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.1745. Min Act: -0.0000

Data Index: 1886924 (The Pile)

Max Activating Token Index: 630

Text #6

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.2015. Min Act: -0.0000

Data Index: 1052803 (The Pile)

Max Activating Token Index: 985

Text #7

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.2224. Min Act: -0.0000

Data Index: 53088 (The Pile)

Max Activating Token Index: 824

Text #8

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.1946. Min Act: -0.0000

Data Index: 1294130 (The Pile)

Max Activating Token Index: 488

Text #9

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.1799. Min Act: -0.0000

Data Index: 1079602 (The Pile)

Max Activating Token Index: 687

Text #10

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.1807. Min Act: -0.0000

Data Index: 1200708 (The Pile)

Max Activating Token Index: 1002

Text #11

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.1804. Min Act: -0.0000

Data Index: 1430873 (The Pile)

Max Activating Token Index: 890

Text #12

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.1874. Min Act: -0.0000

Data Index: 768948 (The Pile)

Max Activating Token Index: 862

Text #13

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.2143. Min Act: -0.0000

Data Index: 1163808 (The Pile)

Max Activating Token Index: 1002

Text #14

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.1620. Min Act: -0.0000

Data Index: 1159149 (The Pile)

Max Activating Token Index: 891

Text #15

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.1873. Min Act: -0.0000

Data Index: 1162784 (The Pile)

Max Activating Token Index: 678

Text #16

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.2067. Min Act: -0.0000

Data Index: 1615518 (The Pile)

Max Activating Token Index: 921

Text #17

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.1892. Min Act: -0.0000

Data Index: 1192669 (The Pile)

Max Activating Token Index: 692

Text #18

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.1889. Min Act: -0.0000

Data Index: 224525 (The Pile)

Max Activating Token Index: 531

Text #19

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.1801. Min Act: -0.0000

Data Index: 478786 (The Pile)

Max Activating Token Index: 619