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

Dataset: The Pile

Neuron 1591 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6825. Min Range: -0.6825

Max Act: 0.6825. Min Act: -0.0000

Data Index: 1002875 (The Pile)

Max Activating Token Index: 990

Text #1

Max Range: 0.6825. Min Range: -0.6825

Max Act: 0.6025. Min Act: -0.0000

Data Index: 488693 (The Pile)

Max Activating Token Index: 54

Text #2

Max Range: 0.6825. Min Range: -0.6825

Max Act: 0.5835. Min Act: -0.0000

Data Index: 146230 (The Pile)

Max Activating Token Index: 170

Text #3

Max Range: 0.6825. Min Range: -0.6825

Max Act: 0.6140. Min Act: -0.0000

Data Index: 1411688 (The Pile)

Max Activating Token Index: 230

Text #4

Max Range: 0.6825. Min Range: -0.6825

Max Act: 0.5808. Min Act: -0.0000

Data Index: 1011075 (The Pile)

Max Activating Token Index: 613

Text #5

Max Range: 0.6825. Min Range: -0.6825

Max Act: 0.5834. Min Act: -0.0000

Data Index: 1351862 (The Pile)

Max Activating Token Index: 114

Text #6

Max Range: 0.6825. Min Range: -0.6825

Max Act: 0.5494. Min Act: -0.0000

Data Index: 1272518 (The Pile)

Max Activating Token Index: 701

Text #7

Max Range: 0.6825. Min Range: -0.6825

Max Act: 0.5337. Min Act: -0.0000

Data Index: 1040068 (The Pile)

Max Activating Token Index: 233

Text #8

Max Range: 0.6825. Min Range: -0.6825

Max Act: 0.5104. Min Act: -0.0000

Data Index: 1512905 (The Pile)

Max Activating Token Index: 402

Text #9

Max Range: 0.6825. Min Range: -0.6825

Max Act: 0.4725. Min Act: -0.0000

Data Index: 1443566 (The Pile)

Max Activating Token Index: 605

Text #10

Max Range: 0.6825. Min Range: -0.6825

Max Act: 0.5205. Min Act: -0.0000

Data Index: 297905 (The Pile)

Max Activating Token Index: 576

Text #11

Max Range: 0.6825. Min Range: -0.6825

Max Act: 0.5090. Min Act: 0.0000

Data Index: 963864 (The Pile)

Max Activating Token Index: 317

Text #12

Max Range: 0.6825. Min Range: -0.6825

Max Act: 0.4555. Min Act: -0.0000

Data Index: 375880 (The Pile)

Max Activating Token Index: 79

Text #13

Max Range: 0.6825. Min Range: -0.6825

Max Act: 0.4852. Min Act: -0.0000

Data Index: 1745311 (The Pile)

Max Activating Token Index: 226

Text #14

Max Range: 0.6825. Min Range: -0.6825

Max Act: 0.4465. Min Act: -0.0000

Data Index: 556607 (The Pile)

Max Activating Token Index: 997

Text #15

Max Range: 0.6825. Min Range: -0.6825

Max Act: 0.4724. Min Act: -0.0000

Data Index: 437239 (The Pile)

Max Activating Token Index: 869

Text #16

Max Range: 0.6825. Min Range: -0.6825

Max Act: 0.4710. Min Act: -0.0000

Data Index: 1050530 (The Pile)

Max Activating Token Index: 129

Text #17

Max Range: 0.6825. Min Range: -0.6825

Max Act: 0.4491. Min Act: -0.0000

Data Index: 494944 (The Pile)

Max Activating Token Index: 63

Text #18

Max Range: 0.6825. Min Range: -0.6825

Max Act: 0.4472. Min Act: -0.0000

Data Index: 1708591 (The Pile)

Max Activating Token Index: 528

Text #19

Max Range: 0.6825. Min Range: -0.6825

Max Act: 0.4607. Min Act: -0.0000

Data Index: 1657538 (The Pile)

Max Activating Token Index: 801