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

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

Neuron 5304 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: 0.6663. Min Range: -0.6663

Max Act: 0.6663. Min Act: -0.0000

Data Index: 844268 (C4 (Web Text))

Max Activating Token Index: 71

Text #1

Max Range: 0.6663. Min Range: -0.6663

Max Act: 0.6302. Min Act: -0.0000

Data Index: 1109639 (C4 (Web Text))

Max Activating Token Index: 149

Text #2

Max Range: 0.6663. Min Range: -0.6663

Max Act: 0.6637. Min Act: -0.0000

Data Index: 591162 (C4 (Web Text))

Max Activating Token Index: 871

Text #3

Max Range: 0.6663. Min Range: -0.6663

Max Act: 0.5680. Min Act: -0.0000

Data Index: 111048 (C4 (Web Text))

Max Activating Token Index: 111

Text #4

Max Range: 0.6663. Min Range: -0.6663

Max Act: 0.5519. Min Act: -0.0000

Data Index: 979853 (C4 (Web Text))

Max Activating Token Index: 804

Text #5

Max Range: 0.6663. Min Range: -0.6663

Max Act: 0.5878. Min Act: -0.0000

Data Index: 336616 (C4 (Web Text))

Max Activating Token Index: 297

Text #6

Max Range: 0.6663. Min Range: -0.6663

Max Act: 0.5634. Min Act: 0.0000

Data Index: 1077300 (C4 (Web Text))

Max Activating Token Index: 937

Text #7

Max Range: 0.6663. Min Range: -0.6663

Max Act: 0.5323. Min Act: -0.0000

Data Index: 714609 (C4 (Web Text))

Max Activating Token Index: 940

Text #8

Max Range: 0.6663. Min Range: -0.6663

Max Act: 0.5658. Min Act: -0.0000

Data Index: 1011376 (C4 (Web Text))

Max Activating Token Index: 182

Text #9

Max Range: 0.6663. Min Range: -0.6663

Max Act: 0.5282. Min Act: -0.0000

Data Index: 776424 (C4 (Web Text))

Max Activating Token Index: 37

Text #10

Max Range: 0.6663. Min Range: -0.6663

Max Act: 0.4638. Min Act: -0.0000

Data Index: 527822 (C4 (Web Text))

Max Activating Token Index: 292

Text #11

Max Range: 0.6663. Min Range: -0.6663

Max Act: 0.4936. Min Act: -0.0000

Data Index: 466777 (C4 (Web Text))

Max Activating Token Index: 583

Text #12

Max Range: 0.6663. Min Range: -0.6663

Max Act: 0.4911. Min Act: -0.0000

Data Index: 616511 (C4 (Web Text))

Max Activating Token Index: 393

Text #13

Max Range: 0.6663. Min Range: -0.6663

Max Act: 0.4865. Min Act: -0.0000

Data Index: 904966 (C4 (Web Text))

Max Activating Token Index: 352

Text #14

Max Range: 0.6663. Min Range: -0.6663

Max Act: 0.4834. Min Act: -0.0000

Data Index: 906933 (C4 (Web Text))

Max Activating Token Index: 728

Text #15

Max Range: 0.6663. Min Range: -0.6663

Max Act: 0.4666. Min Act: 0.0000

Data Index: 1296650 (C4 (Web Text))

Max Activating Token Index: 109

Text #16

Max Range: 0.6663. Min Range: -0.6663

Max Act: 0.4644. Min Act: -0.0000

Data Index: 1238566 (C4 (Web Text))

Max Activating Token Index: 950

Text #17

Max Range: 0.6663. Min Range: -0.6663

Max Act: 0.4659. Min Act: -0.0000

Data Index: 791782 (C4 (Web Text))

Max Activating Token Index: 194

Text #18

Max Range: 0.6663. Min Range: -0.6663

Max Act: 0.4605. Min Act: -0.0000

Data Index: 950841 (C4 (Web Text))

Max Activating Token Index: 511

Text #19

Max Range: 0.6663. Min Range: -0.6663

Max Act: 0.4592. Min Act: -0.0000

Data Index: 1029106 (C4 (Web Text))

Max Activating Token Index: 732