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

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

Neuron 1791 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8014. Min Range: -0.8014

Max Act: 0.8006. Min Act: -0.0000

Data Index: 1640857 (Python Code)

Max Activating Token Index: 818

Text #1

Max Range: 0.8014. Min Range: -0.8014

Max Act: 0.7357. Min Act: -0.0000

Data Index: 1502151 (Python Code)

Max Activating Token Index: 388

Text #2

Max Range: 0.8014. Min Range: -0.8014

Max Act: 0.8014. Min Act: -0.0000

Data Index: 1594153 (Python Code)

Max Activating Token Index: 864

Text #3

Max Range: 0.8014. Min Range: -0.8014

Max Act: 0.7462. Min Act: -0.0000

Data Index: 1594496 (Python Code)

Max Activating Token Index: 87

Text #4

Max Range: 0.8014. Min Range: -0.8014

Max Act: 0.7386. Min Act: -0.0000

Data Index: 1477904 (Python Code)

Max Activating Token Index: 32

Text #5

Max Range: 0.8014. Min Range: -0.8014

Max Act: 0.7049. Min Act: -0.0000

Data Index: 1490302 (Python Code)

Max Activating Token Index: 33

Text #6

Max Range: 0.8014. Min Range: -0.8014

Max Act: 0.6747. Min Act: -0.0000

Data Index: 1598550 (Python Code)

Max Activating Token Index: 707

Text #7

Max Range: 0.8014. Min Range: -0.8014

Max Act: 0.6926. Min Act: -0.0000

Data Index: 1365046 (Python Code)

Max Activating Token Index: 699

Text #8

Max Range: 0.8014. Min Range: -0.8014

Max Act: 0.6803. Min Act: -0.0000

Data Index: 1655827 (Python Code)

Max Activating Token Index: 156

Text #9

Max Range: 0.8014. Min Range: -0.8014

Max Act: 0.6917. Min Act: -0.0000

Data Index: 1509630 (Python Code)

Max Activating Token Index: 89

Text #10

Max Range: 0.8014. Min Range: -0.8014

Max Act: 0.6495. Min Act: -0.0000

Data Index: 1418072 (Python Code)

Max Activating Token Index: 717

Text #11

Max Range: 0.8014. Min Range: -0.8014

Max Act: 0.6845. Min Act: -0.0000

Data Index: 1465434 (Python Code)

Max Activating Token Index: 762

Text #12

Max Range: 0.8014. Min Range: -0.8014

Max Act: 0.6383. Min Act: -0.0000

Data Index: 1360281 (Python Code)

Max Activating Token Index: 528

Text #13

Max Range: 0.8014. Min Range: -0.8014

Max Act: 0.6243. Min Act: -0.0000

Data Index: 1371258 (Python Code)

Max Activating Token Index: 558

Text #14

Max Range: 0.8014. Min Range: -0.8014

Max Act: 0.5891. Min Act: -0.0000

Data Index: 1623507 (Python Code)

Max Activating Token Index: 846

Text #15

Max Range: 0.8014. Min Range: -0.8014

Max Act: 0.6000. Min Act: -0.0000

Data Index: 1423013 (Python Code)

Max Activating Token Index: 589

Text #16

Max Range: 0.8014. Min Range: -0.8014

Max Act: 0.5935. Min Act: -0.0000

Data Index: 1625163 (Python Code)

Max Activating Token Index: 562

Text #17

Max Range: 0.8014. Min Range: -0.8014

Max Act: 0.5896. Min Act: -0.0000

Data Index: 1463014 (Python Code)

Max Activating Token Index: 12

Text #18

Max Range: 0.8014. Min Range: -0.8014

Max Act: 0.6060. Min Act: -0.0000

Data Index: 1562620 (Python Code)

Max Activating Token Index: 35

Text #19

Max Range: 0.8014. Min Range: -0.8014

Max Act: 0.5793. Min Act: -0.0000

Data Index: 1573101 (Python Code)

Max Activating Token Index: 852