Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 670 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.2070. Min Range: -0.2070

Max Act: 0.1943. Min Act: -0.0000

Data Index: 1645979 (Python Code)

Max Activating Token Index: 177

Text #1

Max Range: 0.2070. Min Range: -0.2070

Max Act: 0.1909. Min Act: -0.0000

Data Index: 262598 (C4 (Web Text))

Max Activating Token Index: 470

Text #2

Max Range: 0.2070. Min Range: -0.2070

Max Act: 0.1904. Min Act: -0.0000

Data Index: 384406 (C4 (Web Text))

Max Activating Token Index: 995

Text #3

Max Range: 0.2070. Min Range: -0.2070

Max Act: 0.1938. Min Act: -0.0000

Data Index: 1084459 (C4 (Web Text))

Max Activating Token Index: 531

Text #4

Max Range: 0.2070. Min Range: -0.2070

Max Act: 0.1848. Min Act: -0.0000

Data Index: 1534377 (Python Code)

Max Activating Token Index: 851

Text #5

Max Range: 0.2070. Min Range: -0.2070

Max Act: 0.1877. Min Act: -0.0000

Data Index: 1578340 (Python Code)

Max Activating Token Index: 522

Text #6

Max Range: 0.2070. Min Range: -0.2070

Max Act: 0.1877. Min Act: -0.0000

Data Index: 766044 (C4 (Web Text))

Max Activating Token Index: 105

Text #7

Max Range: 0.2070. Min Range: -0.2070

Max Act: 0.1854. Min Act: -0.0000

Data Index: 1343637 (C4 (Web Text))

Max Activating Token Index: 685

Text #8

Max Range: 0.2070. Min Range: -0.2070

Max Act: 0.1715. Min Act: -0.0000

Data Index: 1589597 (Python Code)

Max Activating Token Index: 198

Text #9

Max Range: 0.2070. Min Range: -0.2070

Max Act: 0.1792. Min Act: -0.0000

Data Index: 1653940 (Python Code)

Max Activating Token Index: 160

Text #10

Max Range: 0.2070. Min Range: -0.2070

Max Act: 0.1782. Min Act: -0.0000

Data Index: 646645 (C4 (Web Text))

Max Activating Token Index: 149

Text #11

Max Range: 0.2070. Min Range: -0.2070

Max Act: 0.2070. Min Act: -0.0000

Data Index: 430253 (C4 (Web Text))

Max Activating Token Index: 1015

Text #12

Max Range: 0.2070. Min Range: -0.2070

Max Act: 0.1819. Min Act: -0.0000

Data Index: 1021259 (C4 (Web Text))

Max Activating Token Index: 884

Text #13

Max Range: 0.2070. Min Range: -0.2070

Max Act: 0.1810. Min Act: -0.0000

Data Index: 1470393 (Python Code)

Max Activating Token Index: 64

Text #14

Max Range: 0.2070. Min Range: -0.2070

Max Act: 0.1726. Min Act: -0.0000

Data Index: 1557266 (Python Code)

Max Activating Token Index: 105

Text #15

Max Range: 0.2070. Min Range: -0.2070

Max Act: 0.1784. Min Act: -0.0000

Data Index: 617133 (C4 (Web Text))

Max Activating Token Index: 893

Text #16

Max Range: 0.2070. Min Range: -0.2070

Max Act: 0.1846. Min Act: -0.0000

Data Index: 1407166 (Python Code)

Max Activating Token Index: 238

Text #17

Max Range: 0.2070. Min Range: -0.2070

Max Act: 0.1584. Min Act: -0.0000

Data Index: 994011 (C4 (Web Text))

Max Activating Token Index: 463

Text #18

Max Range: 0.2070. Min Range: -0.2070

Max Act: 0.1750. Min Act: -0.0000

Data Index: 1354778 (C4 (Web Text))

Max Activating Token Index: 264

Text #19

Max Range: 0.2070. Min Range: -0.2070

Max Act: 0.1654. Min Act: -0.0000

Data Index: 821041 (C4 (Web Text))

Max Activating Token Index: 970