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

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

Neuron 4462 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2683. Min Range: -0.2683

Max Act: 0.2683. Min Act: -0.0000

Data Index: 88387 (C4 (Web Text))

Max Activating Token Index: 835

Text #1

Max Range: 0.2683. Min Range: -0.2683

Max Act: 0.2661. Min Act: -0.0000

Data Index: 793903 (C4 (Web Text))

Max Activating Token Index: 855

Text #2

Max Range: 0.2683. Min Range: -0.2683

Max Act: 0.2624. Min Act: -0.0000

Data Index: 506198 (C4 (Web Text))

Max Activating Token Index: 603

Text #3

Max Range: 0.2683. Min Range: -0.2683

Max Act: 0.2418. Min Act: -0.0000

Data Index: 432531 (C4 (Web Text))

Max Activating Token Index: 602

Text #4

Max Range: 0.2683. Min Range: -0.2683

Max Act: 0.2093. Min Act: -0.0000

Data Index: 1255034 (C4 (Web Text))

Max Activating Token Index: 552

Text #5

Max Range: 0.2683. Min Range: -0.2683

Max Act: 0.2010. Min Act: -0.0000

Data Index: 1355927 (C4 (Web Text))

Max Activating Token Index: 604

Text #6

Max Range: 0.2683. Min Range: -0.2683

Max Act: 0.2011. Min Act: -0.0000

Data Index: 520137 (C4 (Web Text))

Max Activating Token Index: 123

Text #7

Max Range: 0.2683. Min Range: -0.2683

Max Act: 0.2069. Min Act: -0.0000

Data Index: 391763 (C4 (Web Text))

Max Activating Token Index: 893

Text #8

Max Range: 0.2683. Min Range: -0.2683

Max Act: 0.2017. Min Act: -0.0000

Data Index: 237253 (C4 (Web Text))

Max Activating Token Index: 488

Text #9

Max Range: 0.2683. Min Range: -0.2683

Max Act: 0.1852. Min Act: -0.0000

Data Index: 1146340 (C4 (Web Text))

Max Activating Token Index: 30

Text #10

Max Range: 0.2683. Min Range: -0.2683

Max Act: 0.1855. Min Act: -0.0000

Data Index: 800967 (C4 (Web Text))

Max Activating Token Index: 495

Text #11

Max Range: 0.2683. Min Range: -0.2683

Max Act: 0.1985. Min Act: -0.0000

Data Index: 960566 (C4 (Web Text))

Max Activating Token Index: 740

Text #12

Max Range: 0.2683. Min Range: -0.2683

Max Act: 0.1649. Min Act: -0.0000

Data Index: 1235684 (C4 (Web Text))

Max Activating Token Index: 986

Text #13

Max Range: 0.2683. Min Range: -0.2683

Max Act: 0.1716. Min Act: -0.0000

Data Index: 675273 (C4 (Web Text))

Max Activating Token Index: 864

Text #14

Max Range: 0.2683. Min Range: -0.2683

Max Act: 0.1728. Min Act: -0.0000

Data Index: 1470240 (Python Code)

Max Activating Token Index: 456

Text #15

Max Range: 0.2683. Min Range: -0.2683

Max Act: 0.1885. Min Act: -0.0000

Data Index: 465823 (C4 (Web Text))

Max Activating Token Index: 479

Text #16

Max Range: 0.2683. Min Range: -0.2683

Max Act: 0.1725. Min Act: -0.0000

Data Index: 693824 (C4 (Web Text))

Max Activating Token Index: 931

Text #17

Max Range: 0.2683. Min Range: -0.2683

Max Act: 0.1784. Min Act: -0.0000

Data Index: 1139307 (C4 (Web Text))

Max Activating Token Index: 776

Text #18

Max Range: 0.2683. Min Range: -0.2683

Max Act: 0.1632. Min Act: -0.0000

Data Index: 41853 (C4 (Web Text))

Max Activating Token Index: 221

Text #19

Max Range: 0.2683. Min Range: -0.2683

Max Act: 0.1719. Min Act: -0.0000

Data Index: 378267 (C4 (Web Text))

Max Activating Token Index: 624