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

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

Neuron 3456 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: 0.6703. Min Range: -0.6703

Max Act: 0.6703. Min Act: -0.0000

Data Index: 1426948 (Python Code)

Max Activating Token Index: 961

Text #1

Max Range: 0.6703. Min Range: -0.6703

Max Act: 0.6434. Min Act: 0.0000

Data Index: 1443476 (Python Code)

Max Activating Token Index: 893

Text #2

Max Range: 0.6703. Min Range: -0.6703

Max Act: 0.5662. Min Act: -0.0000

Data Index: 581404 (C4 (Web Text))

Max Activating Token Index: 428

Text #3

Max Range: 0.6703. Min Range: -0.6703

Max Act: 0.5772. Min Act: -0.0000

Data Index: 1599834 (Python Code)

Max Activating Token Index: 551

Text #4

Max Range: 0.6703. Min Range: -0.6703

Max Act: 0.5632. Min Act: -0.0000

Data Index: 1420003 (Python Code)

Max Activating Token Index: 89

Text #5

Max Range: 0.6703. Min Range: -0.6703

Max Act: 0.5613. Min Act: -0.0000

Data Index: 1405140 (Python Code)

Max Activating Token Index: 719

Text #6

Max Range: 0.6703. Min Range: -0.6703

Max Act: 0.5440. Min Act: 0.0001

Data Index: 1612169 (Python Code)

Max Activating Token Index: 55

Text #7

Max Range: 0.6703. Min Range: -0.6703

Max Act: 0.5223. Min Act: 0.0000

Data Index: 1392495 (Python Code)

Max Activating Token Index: 890

Text #8

Max Range: 0.6703. Min Range: -0.6703

Max Act: 0.5016. Min Act: 0.0000

Data Index: 1279129 (C4 (Web Text))

Max Activating Token Index: 241

Text #9

Max Range: 0.6703. Min Range: -0.6703

Max Act: 0.4949. Min Act: 0.0000

Data Index: 203593 (C4 (Web Text))

Max Activating Token Index: 752

Text #10

Max Range: 0.6703. Min Range: -0.6703

Max Act: 0.4948. Min Act: 0.0001

Data Index: 1483784 (Python Code)

Max Activating Token Index: 882

Text #11

Max Range: 0.6703. Min Range: -0.6703

Max Act: 0.4850. Min Act: -0.0000

Data Index: 1391959 (Python Code)

Max Activating Token Index: 946

Text #12

Max Range: 0.6703. Min Range: -0.6703

Max Act: 0.4798. Min Act: 0.0000

Data Index: 1424771 (Python Code)

Max Activating Token Index: 769

Text #13

Max Range: 0.6703. Min Range: -0.6703

Max Act: 0.4774. Min Act: -0.0000

Data Index: 1547480 (Python Code)

Max Activating Token Index: 347

Text #14

Max Range: 0.6703. Min Range: -0.6703

Max Act: 0.4585. Min Act: 0.0000

Data Index: 366069 (C4 (Web Text))

Max Activating Token Index: 287

Text #15

Max Range: 0.6703. Min Range: -0.6703

Max Act: 0.4552. Min Act: 0.0001

Data Index: 1366871 (Python Code)

Max Activating Token Index: 981

Text #16

Max Range: 0.6703. Min Range: -0.6703

Max Act: 0.4631. Min Act: -0.0000

Data Index: 1432069 (Python Code)

Max Activating Token Index: 967

Text #17

Max Range: 0.6703. Min Range: -0.6703

Max Act: 0.4431. Min Act: -0.0000

Data Index: 1587454 (Python Code)

Max Activating Token Index: 29

Text #18

Max Range: 0.6703. Min Range: -0.6703

Max Act: 0.4369. Min Act: -0.0000

Data Index: 819130 (C4 (Web Text))

Max Activating Token Index: 565

Text #19

Max Range: 0.6703. Min Range: -0.6703

Max Act: 0.4518. Min Act: 0.0001

Data Index: 1364034 (Python Code)

Max Activating Token Index: 90