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

Dataset: The Pile

Neuron 3726 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: 0.3853. Min Range: -0.3853

Max Act: 0.3853. Min Act: -0.0000

Data Index: 1736010 (The Pile)

Max Activating Token Index: 1002

Text #1

Max Range: 0.3853. Min Range: -0.3853

Max Act: 0.2834. Min Act: -0.0000

Data Index: 1872382 (The Pile)

Max Activating Token Index: 948

Text #2

Max Range: 0.3853. Min Range: -0.3853

Max Act: 0.2746. Min Act: -0.0000

Data Index: 862922 (The Pile)

Max Activating Token Index: 586

Text #3

Max Range: 0.3853. Min Range: -0.3853

Max Act: 0.2472. Min Act: -0.0000

Data Index: 141779 (The Pile)

Max Activating Token Index: 915

Text #4

Max Range: 0.3853. Min Range: -0.3853

Max Act: 0.2555. Min Act: -0.0000

Data Index: 261628 (The Pile)

Max Activating Token Index: 218

Text #5

Max Range: 0.3853. Min Range: -0.3853

Max Act: 0.2465. Min Act: -0.0000

Data Index: 1892907 (The Pile)

Max Activating Token Index: 608

Text #6

Max Range: 0.3853. Min Range: -0.3853

Max Act: 0.2462. Min Act: -0.0000

Data Index: 1912433 (The Pile)

Max Activating Token Index: 487

Text #7

Max Range: 0.3853. Min Range: -0.3853

Max Act: 0.2375. Min Act: -0.0000

Data Index: 285398 (The Pile)

Max Activating Token Index: 954

Text #8

Max Range: 0.3853. Min Range: -0.3853

Max Act: 0.2348. Min Act: -0.0000

Data Index: 684452 (The Pile)

Max Activating Token Index: 276

Text #9

Max Range: 0.3853. Min Range: -0.3853

Max Act: 0.2122. Min Act: -0.0000

Data Index: 1505619 (The Pile)

Max Activating Token Index: 876

Text #10

Max Range: 0.3853. Min Range: -0.3853

Max Act: 0.2212. Min Act: -0.0000

Data Index: 1194029 (The Pile)

Max Activating Token Index: 748

Text #11

Max Range: 0.3853. Min Range: -0.3853

Max Act: 0.2064. Min Act: -0.0000

Data Index: 426963 (The Pile)

Max Activating Token Index: 326

Text #12

Max Range: 0.3853. Min Range: -0.3853

Max Act: 0.2095. Min Act: -0.0000

Data Index: 583765 (The Pile)

Max Activating Token Index: 179

Text #13

Max Range: 0.3853. Min Range: -0.3853

Max Act: 0.1968. Min Act: -0.0000

Data Index: 1718753 (The Pile)

Max Activating Token Index: 893

Text #14

Max Range: 0.3853. Min Range: -0.3853

Max Act: 0.2160. Min Act: -0.0000

Data Index: 1798392 (The Pile)

Max Activating Token Index: 408

Text #15

Max Range: 0.3853. Min Range: -0.3853

Max Act: 0.2046. Min Act: -0.0000

Data Index: 826895 (The Pile)

Max Activating Token Index: 706

Text #16

Max Range: 0.3853. Min Range: -0.3853

Max Act: 0.1947. Min Act: -0.0000

Data Index: 107400 (The Pile)

Max Activating Token Index: 1016

Text #17

Max Range: 0.3853. Min Range: -0.3853

Max Act: 0.2245. Min Act: -0.0000

Data Index: 1902030 (The Pile)

Max Activating Token Index: 968

Text #18

Max Range: 0.3853. Min Range: -0.3853

Max Act: 0.2079. Min Act: -0.0000

Data Index: 1233589 (The Pile)

Max Activating Token Index: 418

Text #19

Max Range: 0.3853. Min Range: -0.3853

Max Act: 0.1848. Min Act: -0.0000

Data Index: 483533 (The Pile)

Max Activating Token Index: 603