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

Dataset: The Pile

Neuron 858 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: 1.5921. Min Range: -1.5921

Max Act: 1.5921. Min Act: -0.0000

Data Index: 1117914 (The Pile)

Max Activating Token Index: 346

Text #1

Max Range: 1.5921. Min Range: -1.5921

Max Act: 1.2652. Min Act: -0.0000

Data Index: 14377 (The Pile)

Max Activating Token Index: 832

Text #2

Max Range: 1.5921. Min Range: -1.5921

Max Act: 1.3065. Min Act: -0.0000

Data Index: 1871711 (The Pile)

Max Activating Token Index: 625

Text #3

Max Range: 1.5921. Min Range: -1.5921

Max Act: 1.2005. Min Act: -0.0000

Data Index: 759998 (The Pile)

Max Activating Token Index: 704

Text #4

Max Range: 1.5921. Min Range: -1.5921

Max Act: 1.2037. Min Act: -0.0000

Data Index: 1950848 (The Pile)

Max Activating Token Index: 205

Text #5

Max Range: 1.5921. Min Range: -1.5921

Max Act: 1.1461. Min Act: -0.0000

Data Index: 737422 (The Pile)

Max Activating Token Index: 932

Text #6

Max Range: 1.5921. Min Range: -1.5921

Max Act: 1.1303. Min Act: -0.0000

Data Index: 528694 (The Pile)

Max Activating Token Index: 952

Text #7

Max Range: 1.5921. Min Range: -1.5921

Max Act: 1.1996. Min Act: -0.0000

Data Index: 1631719 (The Pile)

Max Activating Token Index: 539

Text #8

Max Range: 1.5921. Min Range: -1.5921

Max Act: 1.1067. Min Act: -0.0000

Data Index: 157240 (The Pile)

Max Activating Token Index: 936

Text #9

Max Range: 1.5921. Min Range: -1.5921

Max Act: 1.1022. Min Act: -0.0000

Data Index: 1205979 (The Pile)

Max Activating Token Index: 580

Text #10

Max Range: 1.5921. Min Range: -1.5921

Max Act: 1.2484. Min Act: -0.0000

Data Index: 1471705 (The Pile)

Max Activating Token Index: 638

Text #11

Max Range: 1.5921. Min Range: -1.5921

Max Act: 1.2620. Min Act: -0.0000

Data Index: 868152 (The Pile)

Max Activating Token Index: 951

Text #12

Max Range: 1.5921. Min Range: -1.5921

Max Act: 1.1684. Min Act: -0.0000

Data Index: 850531 (The Pile)

Max Activating Token Index: 333

Text #13

Max Range: 1.5921. Min Range: -1.5921

Max Act: 1.1998. Min Act: -0.0000

Data Index: 1526983 (The Pile)

Max Activating Token Index: 555

Text #14

Max Range: 1.5921. Min Range: -1.5921

Max Act: 1.2061. Min Act: -0.0000

Data Index: 95494 (The Pile)

Max Activating Token Index: 1012

Text #15

Max Range: 1.5921. Min Range: -1.5921

Max Act: 1.0845. Min Act: -0.0000

Data Index: 999805 (The Pile)

Max Activating Token Index: 564

Text #16

Max Range: 1.5921. Min Range: -1.5921

Max Act: 1.2618. Min Act: -0.0000

Data Index: 380490 (The Pile)

Max Activating Token Index: 736

Text #17

Max Range: 1.5921. Min Range: -1.5921

Max Act: 1.0512. Min Act: -0.0000

Data Index: 1274902 (The Pile)

Max Activating Token Index: 795

Text #18

Max Range: 1.5921. Min Range: -1.5921

Max Act: 1.1113. Min Act: -0.0000

Data Index: 1262325 (The Pile)

Max Activating Token Index: 593

Text #19

Max Range: 1.5921. Min Range: -1.5921

Max Act: 1.0826. Min Act: -0.0000

Data Index: 992423 (The Pile)

Max Activating Token Index: 646