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

Dataset: The Pile

Neuron 876 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.5976. Min Range: -5.5976

Max Act: 5.5976. Min Act: -0.0000

Data Index: 966768 (The Pile)

Max Activating Token Index: 912

Text #1

Max Range: 5.5976. Min Range: -5.5976

Max Act: 4.7618. Min Act: -0.0000

Data Index: 1410908 (The Pile)

Max Activating Token Index: 197

Text #2

Max Range: 5.5976. Min Range: -5.5976

Max Act: 4.4338. Min Act: -0.0000

Data Index: 885078 (The Pile)

Max Activating Token Index: 1008

Text #3

Max Range: 5.5976. Min Range: -5.5976

Max Act: 4.3194. Min Act: -0.0000

Data Index: 1147 (The Pile)

Max Activating Token Index: 90

Text #4

Max Range: 5.5976. Min Range: -5.5976

Max Act: 4.2344. Min Act: -0.0000

Data Index: 1656941 (The Pile)

Max Activating Token Index: 13

Text #5

Max Range: 5.5976. Min Range: -5.5976

Max Act: 4.1330. Min Act: -0.0000

Data Index: 415784 (The Pile)

Max Activating Token Index: 868

Text #6

Max Range: 5.5976. Min Range: -5.5976

Max Act: 3.8773. Min Act: -0.0000

Data Index: 527620 (The Pile)

Max Activating Token Index: 996

Text #7

Max Range: 5.5976. Min Range: -5.5976

Max Act: 3.7121. Min Act: -0.0000

Data Index: 245946 (The Pile)

Max Activating Token Index: 152

Text #8

Max Range: 5.5976. Min Range: -5.5976

Max Act: 3.8715. Min Act: -0.0000

Data Index: 1088263 (The Pile)

Max Activating Token Index: 626

Text #9

Max Range: 5.5976. Min Range: -5.5976

Max Act: 3.6007. Min Act: -0.0000

Data Index: 196298 (The Pile)

Max Activating Token Index: 795

Text #10

Max Range: 5.5976. Min Range: -5.5976

Max Act: 3.7004. Min Act: -0.0000

Data Index: 841749 (The Pile)

Max Activating Token Index: 424

Text #11

Max Range: 5.5976. Min Range: -5.5976

Max Act: 3.6728. Min Act: -0.0000

Data Index: 365429 (The Pile)

Max Activating Token Index: 10

Text #12

Max Range: 5.5976. Min Range: -5.5976

Max Act: 3.4196. Min Act: -0.0000

Data Index: 1975107 (The Pile)

Max Activating Token Index: 9

Text #13

Max Range: 5.5976. Min Range: -5.5976

Max Act: 3.5758. Min Act: -0.0000

Data Index: 517667 (The Pile)

Max Activating Token Index: 479

Text #14

Max Range: 5.5976. Min Range: -5.5976

Max Act: 3.5634. Min Act: -0.0000

Data Index: 1938764 (The Pile)

Max Activating Token Index: 1018

Text #15

Max Range: 5.5976. Min Range: -5.5976

Max Act: 3.3100. Min Act: -0.0000

Data Index: 1427266 (The Pile)

Max Activating Token Index: 421

Text #16

Max Range: 5.5976. Min Range: -5.5976

Max Act: 3.2298. Min Act: -0.0000

Data Index: 672008 (The Pile)

Max Activating Token Index: 655

Text #17

Max Range: 5.5976. Min Range: -5.5976

Max Act: 3.2085. Min Act: -0.0000

Data Index: 465034 (The Pile)

Max Activating Token Index: 927

Text #18

Max Range: 5.5976. Min Range: -5.5976

Max Act: 3.2096. Min Act: -0.0000

Data Index: 1831498 (The Pile)

Max Activating Token Index: 44

Text #19

Max Range: 5.5976. Min Range: -5.5976

Max Act: 3.1802. Min Act: -0.0000

Data Index: 108147 (The Pile)

Max Activating Token Index: 222