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

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

Neuron 4486 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: 0.2452. Min Range: -0.2452

Max Act: 0.2452. Min Act: -0.0001

Data Index: 65629 (C4 (Web Text))

Max Activating Token Index: 34

Text #1

Max Range: 0.2452. Min Range: -0.2452

Max Act: 0.2265. Min Act: -0.0001

Data Index: 115516 (C4 (Web Text))

Max Activating Token Index: 363

Text #2

Max Range: 0.2452. Min Range: -0.2452

Max Act: 0.2207. Min Act: -0.0001

Data Index: 956673 (C4 (Web Text))

Max Activating Token Index: 530

Text #3

Max Range: 0.2452. Min Range: -0.2452

Max Act: 0.1919. Min Act: -0.0001

Data Index: 599667 (C4 (Web Text))

Max Activating Token Index: 717

Text #4

Max Range: 0.2452. Min Range: -0.2452

Max Act: 0.1936. Min Act: -0.0001

Data Index: 719302 (C4 (Web Text))

Max Activating Token Index: 881

Text #5

Max Range: 0.2452. Min Range: -0.2452

Max Act: 0.1948. Min Act: -0.0001

Data Index: 1356793 (C4 (Web Text))

Max Activating Token Index: 967

Text #6

Max Range: 0.2452. Min Range: -0.2452

Max Act: 0.1924. Min Act: -0.0001

Data Index: 221486 (C4 (Web Text))

Max Activating Token Index: 960

Text #7

Max Range: 0.2452. Min Range: -0.2452

Max Act: 0.1908. Min Act: -0.0001

Data Index: 366371 (C4 (Web Text))

Max Activating Token Index: 872

Text #8

Max Range: 0.2452. Min Range: -0.2452

Max Act: 0.1759. Min Act: -0.0001

Data Index: 1269749 (C4 (Web Text))

Max Activating Token Index: 794

Text #9

Max Range: 0.2452. Min Range: -0.2452

Max Act: 0.1792. Min Act: -0.0001

Data Index: 70047 (C4 (Web Text))

Max Activating Token Index: 666

Text #10

Max Range: 0.2452. Min Range: -0.2452

Max Act: 0.1755. Min Act: -0.0001

Data Index: 566967 (C4 (Web Text))

Max Activating Token Index: 131

Text #11

Max Range: 0.2452. Min Range: -0.2452

Max Act: 0.1714. Min Act: -0.0001

Data Index: 1220709 (C4 (Web Text))

Max Activating Token Index: 749

Text #12

Max Range: 0.2452. Min Range: -0.2452

Max Act: 0.1685. Min Act: -0.0001

Data Index: 1001169 (C4 (Web Text))

Max Activating Token Index: 774

Text #13

Max Range: 0.2452. Min Range: -0.2452

Max Act: 0.1650. Min Act: -0.0001

Data Index: 59494 (C4 (Web Text))

Max Activating Token Index: 575

Text #14

Max Range: 0.2452. Min Range: -0.2452

Max Act: 0.1686. Min Act: -0.0001

Data Index: 584141 (C4 (Web Text))

Max Activating Token Index: 644

Text #15

Max Range: 0.2452. Min Range: -0.2452

Max Act: 0.1596. Min Act: -0.0001

Data Index: 1219024 (C4 (Web Text))

Max Activating Token Index: 488

Text #16

Max Range: 0.2452. Min Range: -0.2452

Max Act: 0.1594. Min Act: -0.0001

Data Index: 40050 (C4 (Web Text))

Max Activating Token Index: 160

Text #17

Max Range: 0.2452. Min Range: -0.2452

Max Act: 0.1634. Min Act: -0.0001

Data Index: 140329 (C4 (Web Text))

Max Activating Token Index: 593

Text #18

Max Range: 0.2452. Min Range: -0.2452

Max Act: 0.1511. Min Act: -0.0001

Data Index: 717638 (C4 (Web Text))

Max Activating Token Index: 775

Text #19

Max Range: 0.2452. Min Range: -0.2452

Max Act: 0.1611. Min Act: -0.0001

Data Index: 249074 (C4 (Web Text))

Max Activating Token Index: 8