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

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

Neuron 4195 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8755. Min Range: -2.8755

Max Act: 2.7313. Min Act: -0.0001

Data Index: 1460883 (Python Code)

Max Activating Token Index: 429

Text #1

Max Range: 2.8755. Min Range: -2.8755

Max Act: 2.7704. Min Act: -0.0000

Data Index: 1587872 (Python Code)

Max Activating Token Index: 5

Text #2

Max Range: 2.8755. Min Range: -2.8755

Max Act: 2.7704. Min Act: -0.0001

Data Index: 1418754 (Python Code)

Max Activating Token Index: 5

Text #3

Max Range: 2.8755. Min Range: -2.8755

Max Act: 2.7704. Min Act: -0.0000

Data Index: 1559755 (Python Code)

Max Activating Token Index: 5

Text #4

Max Range: 2.8755. Min Range: -2.8755

Max Act: 2.7704. Min Act: -0.0001

Data Index: 1530757 (Python Code)

Max Activating Token Index: 5

Text #5

Max Range: 2.8755. Min Range: -2.8755

Max Act: 2.7704. Min Act: -0.0000

Data Index: 1565997 (Python Code)

Max Activating Token Index: 5

Text #6

Max Range: 2.8755. Min Range: -2.8755

Max Act: 2.7704. Min Act: -0.0000

Data Index: 1519088 (Python Code)

Max Activating Token Index: 5

Text #7

Max Range: 2.8755. Min Range: -2.8755

Max Act: 2.7704. Min Act: -0.0001

Data Index: 1495436 (Python Code)

Max Activating Token Index: 5

Text #8

Max Range: 2.8755. Min Range: -2.8755

Max Act: 2.7704. Min Act: -0.0001

Data Index: 1517914 (Python Code)

Max Activating Token Index: 5

Text #9

Max Range: 2.8755. Min Range: -2.8755

Max Act: 2.7704. Min Act: -0.0000

Data Index: 1361554 (Python Code)

Max Activating Token Index: 5

Text #10

Max Range: 2.8755. Min Range: -2.8755

Max Act: 2.8755. Min Act: -0.0001

Data Index: 1470122 (Python Code)

Max Activating Token Index: 329

Text #11

Max Range: 2.8755. Min Range: -2.8755

Max Act: 2.6475. Min Act: -0.0001

Data Index: 1386007 (Python Code)

Max Activating Token Index: 6

Text #12

Max Range: 2.8755. Min Range: -2.8755

Max Act: 2.6306. Min Act: -0.0000

Data Index: 1506093 (Python Code)

Max Activating Token Index: 522

Text #13

Max Range: 2.8755. Min Range: -2.8755

Max Act: 2.7047. Min Act: -0.0001

Data Index: 1532042 (Python Code)

Max Activating Token Index: 682

Text #14

Max Range: 2.8755. Min Range: -2.8755

Max Act: 2.4633. Min Act: -0.0000

Data Index: 1444613 (Python Code)

Max Activating Token Index: 390

Text #15

Max Range: 2.8755. Min Range: -2.8755

Max Act: 2.5618. Min Act: -0.0001

Data Index: 1652962 (Python Code)

Max Activating Token Index: 436

Text #16

Max Range: 2.8755. Min Range: -2.8755

Max Act: 2.5406. Min Act: -0.0000

Data Index: 1374849 (Python Code)

Max Activating Token Index: 681

Text #17

Max Range: 2.8755. Min Range: -2.8755

Max Act: 2.5460. Min Act: -0.0001

Data Index: 1645734 (Python Code)

Max Activating Token Index: 778

Text #18

Max Range: 2.8755. Min Range: -2.8755

Max Act: 2.5216. Min Act: -0.0001

Data Index: 1579659 (Python Code)

Max Activating Token Index: 7

Text #19

Max Range: 2.8755. Min Range: -2.8755

Max Act: 2.5095. Min Act: -0.0000

Data Index: 1362448 (Python Code)

Max Activating Token Index: 5