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

Dataset: The Pile

Neuron 2243 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7746. Min Range: -0.7746

Max Act: 0.7746. Min Act: -0.0000

Data Index: 1023852 (The Pile)

Max Activating Token Index: 523

Text #1

Max Range: 0.7746. Min Range: -0.7746

Max Act: 0.7179. Min Act: -0.0000

Data Index: 822226 (The Pile)

Max Activating Token Index: 387

Text #2

Max Range: 0.7746. Min Range: -0.7746

Max Act: 0.7311. Min Act: -0.0000

Data Index: 157110 (The Pile)

Max Activating Token Index: 609

Text #3

Max Range: 0.7746. Min Range: -0.7746

Max Act: 0.6874. Min Act: -0.0000

Data Index: 474041 (The Pile)

Max Activating Token Index: 459

Text #4

Max Range: 0.7746. Min Range: -0.7746

Max Act: 0.6819. Min Act: -0.0000

Data Index: 952149 (The Pile)

Max Activating Token Index: 742

Text #5

Max Range: 0.7746. Min Range: -0.7746

Max Act: 0.6667. Min Act: -0.0000

Data Index: 976340 (The Pile)

Max Activating Token Index: 444

Text #6

Max Range: 0.7746. Min Range: -0.7746

Max Act: 0.6382. Min Act: -0.0000

Data Index: 1526965 (The Pile)

Max Activating Token Index: 380

Text #7

Max Range: 0.7746. Min Range: -0.7746

Max Act: 0.6375. Min Act: -0.0000

Data Index: 1729043 (The Pile)

Max Activating Token Index: 351

Text #8

Max Range: 0.7746. Min Range: -0.7746

Max Act: 0.6273. Min Act: -0.0000

Data Index: 1919888 (The Pile)

Max Activating Token Index: 531

Text #9

Max Range: 0.7746. Min Range: -0.7746

Max Act: 0.6229. Min Act: -0.0000

Data Index: 614908 (The Pile)

Max Activating Token Index: 960

Text #10

Max Range: 0.7746. Min Range: -0.7746

Max Act: 0.6413. Min Act: -0.0000

Data Index: 875157 (The Pile)

Max Activating Token Index: 467

Text #11

Max Range: 0.7746. Min Range: -0.7746

Max Act: 0.5834. Min Act: -0.0000

Data Index: 1953962 (The Pile)

Max Activating Token Index: 616

Text #12

Max Range: 0.7746. Min Range: -0.7746

Max Act: 0.5435. Min Act: -0.0000

Data Index: 186558 (The Pile)

Max Activating Token Index: 699

Text #13

Max Range: 0.7746. Min Range: -0.7746

Max Act: 0.5938. Min Act: -0.0000

Data Index: 488014 (The Pile)

Max Activating Token Index: 347

Text #14

Max Range: 0.7746. Min Range: -0.7746

Max Act: 0.5789. Min Act: -0.0000

Data Index: 1023797 (The Pile)

Max Activating Token Index: 842

Text #15

Max Range: 0.7746. Min Range: -0.7746

Max Act: 0.5739. Min Act: -0.0000

Data Index: 1001828 (The Pile)

Max Activating Token Index: 137

Text #16

Max Range: 0.7746. Min Range: -0.7746

Max Act: 0.5261. Min Act: -0.0000

Data Index: 1843911 (The Pile)

Max Activating Token Index: 938

Text #17

Max Range: 0.7746. Min Range: -0.7746

Max Act: 0.6082. Min Act: -0.0000

Data Index: 1739076 (The Pile)

Max Activating Token Index: 769

Text #18

Max Range: 0.7746. Min Range: -0.7746

Max Act: 0.6115. Min Act: -0.0000

Data Index: 379979 (The Pile)

Max Activating Token Index: 357

Text #19

Max Range: 0.7746. Min Range: -0.7746

Max Act: 0.5764. Min Act: -0.0000

Data Index: 1111130 (The Pile)

Max Activating Token Index: 787