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

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

Neuron 3490 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8417. Min Range: -1.8417

Max Act: 1.8417. Min Act: -0.0001

Data Index: 1495481 (Python Code)

Max Activating Token Index: 225

Text #1

Max Range: 1.8417. Min Range: -1.8417

Max Act: 1.6646. Min Act: -0.0000

Data Index: 1491406 (Python Code)

Max Activating Token Index: 860

Text #2

Max Range: 1.8417. Min Range: -1.8417

Max Act: 1.5009. Min Act: -0.0001

Data Index: 1373144 (Python Code)

Max Activating Token Index: 835

Text #3

Max Range: 1.8417. Min Range: -1.8417

Max Act: 1.5150. Min Act: -0.0000

Data Index: 1434688 (Python Code)

Max Activating Token Index: 932

Text #4

Max Range: 1.8417. Min Range: -1.8417

Max Act: 1.5534. Min Act: -0.0000

Data Index: 1470995 (Python Code)

Max Activating Token Index: 921

Text #5

Max Range: 1.8417. Min Range: -1.8417

Max Act: 1.4456. Min Act: -0.0000

Data Index: 1650454 (Python Code)

Max Activating Token Index: 256

Text #6

Max Range: 1.8417. Min Range: -1.8417

Max Act: 1.3940. Min Act: -0.0000

Data Index: 1443203 (Python Code)

Max Activating Token Index: 655

Text #7

Max Range: 1.8417. Min Range: -1.8417

Max Act: 1.5465. Min Act: -0.0000

Data Index: 1415146 (Python Code)

Max Activating Token Index: 866

Text #8

Max Range: 1.8417. Min Range: -1.8417

Max Act: 1.5042. Min Act: -0.0001

Data Index: 1624726 (Python Code)

Max Activating Token Index: 692

Text #9

Max Range: 1.8417. Min Range: -1.8417

Max Act: 1.5226. Min Act: -0.0001

Data Index: 1516225 (Python Code)

Max Activating Token Index: 878

Text #10

Max Range: 1.8417. Min Range: -1.8417

Max Act: 1.3642. Min Act: -0.0000

Data Index: 1495568 (Python Code)

Max Activating Token Index: 742

Text #11

Max Range: 1.8417. Min Range: -1.8417

Max Act: 1.4790. Min Act: -0.0000

Data Index: 1585093 (Python Code)

Max Activating Token Index: 904

Text #12

Max Range: 1.8417. Min Range: -1.8417

Max Act: 1.5595. Min Act: -0.0001

Data Index: 1389829 (Python Code)

Max Activating Token Index: 387

Text #13

Max Range: 1.8417. Min Range: -1.8417

Max Act: 1.6067. Min Act: -0.0001

Data Index: 1436923 (Python Code)

Max Activating Token Index: 890

Text #14

Max Range: 1.8417. Min Range: -1.8417

Max Act: 1.5468. Min Act: -0.0000

Data Index: 1567925 (Python Code)

Max Activating Token Index: 783

Text #15

Max Range: 1.8417. Min Range: -1.8417

Max Act: 1.6149. Min Act: -0.0000

Data Index: 1471902 (Python Code)

Max Activating Token Index: 806

Text #16

Max Range: 1.8417. Min Range: -1.8417

Max Act: 1.3517. Min Act: -0.0000

Data Index: 1646516 (Python Code)

Max Activating Token Index: 696

Text #17

Max Range: 1.8417. Min Range: -1.8417

Max Act: 1.4575. Min Act: -0.0001

Data Index: 1443777 (Python Code)

Max Activating Token Index: 949

Text #18

Max Range: 1.8417. Min Range: -1.8417

Max Act: 1.4414. Min Act: -0.0001

Data Index: 1468697 (Python Code)

Max Activating Token Index: 825

Text #19

Max Range: 1.8417. Min Range: -1.8417

Max Act: 1.5741. Min Act: -0.0000

Data Index: 1621327 (Python Code)

Max Activating Token Index: 657