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

Dataset: The Pile

Neuron 4012 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2669. Min Range: -0.2669

Max Act: 0.2669. Min Act: -0.0000

Data Index: 1874254 (The Pile)

Max Activating Token Index: 255

Text #1

Max Range: 0.2669. Min Range: -0.2669

Max Act: 0.2054. Min Act: -0.0000

Data Index: 563467 (The Pile)

Max Activating Token Index: 988

Text #2

Max Range: 0.2669. Min Range: -0.2669

Max Act: 0.2160. Min Act: -0.0000

Data Index: 565345 (The Pile)

Max Activating Token Index: 68

Text #3

Max Range: 0.2669. Min Range: -0.2669

Max Act: 0.2024. Min Act: -0.0000

Data Index: 1905374 (The Pile)

Max Activating Token Index: 932

Text #4

Max Range: 0.2669. Min Range: -0.2669

Max Act: 0.1922. Min Act: -0.0000

Data Index: 1533636 (The Pile)

Max Activating Token Index: 734

Text #5

Max Range: 0.2669. Min Range: -0.2669

Max Act: 0.1884. Min Act: -0.0000

Data Index: 1443569 (The Pile)

Max Activating Token Index: 268

Text #6

Max Range: 0.2669. Min Range: -0.2669

Max Act: 0.1797. Min Act: -0.0000

Data Index: 658117 (The Pile)

Max Activating Token Index: 603

Text #7

Max Range: 0.2669. Min Range: -0.2669

Max Act: 0.1915. Min Act: -0.0000

Data Index: 1541838 (The Pile)

Max Activating Token Index: 271

Text #8

Max Range: 0.2669. Min Range: -0.2669

Max Act: 0.1764. Min Act: -0.0000

Data Index: 1460632 (The Pile)

Max Activating Token Index: 567

Text #9

Max Range: 0.2669. Min Range: -0.2669

Max Act: 0.1892. Min Act: -0.0000

Data Index: 1035478 (The Pile)

Max Activating Token Index: 181

Text #10

Max Range: 0.2669. Min Range: -0.2669

Max Act: 0.1745. Min Act: -0.0000

Data Index: 461452 (The Pile)

Max Activating Token Index: 771

Text #11

Max Range: 0.2669. Min Range: -0.2669

Max Act: 0.1836. Min Act: -0.0000

Data Index: 387839 (The Pile)

Max Activating Token Index: 1001

Text #12

Max Range: 0.2669. Min Range: -0.2669

Max Act: 0.1828. Min Act: -0.0000

Data Index: 1144771 (The Pile)

Max Activating Token Index: 232

Text #13

Max Range: 0.2669. Min Range: -0.2669

Max Act: 0.1889. Min Act: -0.0000

Data Index: 582924 (The Pile)

Max Activating Token Index: 1017

Text #14

Max Range: 0.2669. Min Range: -0.2669

Max Act: 0.1761. Min Act: -0.0000

Data Index: 959063 (The Pile)

Max Activating Token Index: 253

Text #15

Max Range: 0.2669. Min Range: -0.2669

Max Act: 0.1773. Min Act: -0.0000

Data Index: 1014014 (The Pile)

Max Activating Token Index: 718

Text #16

Max Range: 0.2669. Min Range: -0.2669

Max Act: 0.1864. Min Act: -0.0000

Data Index: 716611 (The Pile)

Max Activating Token Index: 782

Text #17

Max Range: 0.2669. Min Range: -0.2669

Max Act: 0.1797. Min Act: -0.0000

Data Index: 1213984 (The Pile)

Max Activating Token Index: 229

Text #18

Max Range: 0.2669. Min Range: -0.2669

Max Act: 0.1775. Min Act: -0.0000

Data Index: 839315 (The Pile)

Max Activating Token Index: 858

Text #19

Max Range: 0.2669. Min Range: -0.2669

Max Act: 0.1722. Min Act: -0.0000

Data Index: 1279699 (The Pile)

Max Activating Token Index: 272