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

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

Neuron 1821 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: 0.1038. Min Range: -0.1038

Max Act: 0.1038. Min Act: -0.0001

Data Index: 1473702 (Python Code)

Max Activating Token Index: 123

Text #1

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0998. Min Act: -0.0001

Data Index: 545607 (C4 (Web Text))

Max Activating Token Index: 19

Text #2

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0927. Min Act: -0.0001

Data Index: 836947 (C4 (Web Text))

Max Activating Token Index: 747

Text #3

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0933. Min Act: -0.0001

Data Index: 1178980 (C4 (Web Text))

Max Activating Token Index: 941

Text #4

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0899. Min Act: -0.0001

Data Index: 1555917 (Python Code)

Max Activating Token Index: 784

Text #5

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0814. Min Act: -0.0001

Data Index: 1598792 (Python Code)

Max Activating Token Index: 839

Text #6

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0895. Min Act: -0.0001

Data Index: 638535 (C4 (Web Text))

Max Activating Token Index: 312

Text #7

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0831. Min Act: -0.0001

Data Index: 1145339 (C4 (Web Text))

Max Activating Token Index: 504

Text #8

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0832. Min Act: -0.0001

Data Index: 757414 (C4 (Web Text))

Max Activating Token Index: 534

Text #9

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0876. Min Act: -0.0001

Data Index: 178739 (C4 (Web Text))

Max Activating Token Index: 996

Text #10

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0777. Min Act: -0.0001

Data Index: 1282764 (C4 (Web Text))

Max Activating Token Index: 74

Text #11

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0799. Min Act: -0.0001

Data Index: 1255655 (C4 (Web Text))

Max Activating Token Index: 304

Text #12

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0839. Min Act: -0.0001

Data Index: 362402 (C4 (Web Text))

Max Activating Token Index: 608

Text #13

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0834. Min Act: -0.0001

Data Index: 331603 (C4 (Web Text))

Max Activating Token Index: 329

Text #14

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0771. Min Act: -0.0001

Data Index: 1625485 (Python Code)

Max Activating Token Index: 843

Text #15

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0748. Min Act: -0.0001

Data Index: 713810 (C4 (Web Text))

Max Activating Token Index: 189

Text #16

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0829. Min Act: -0.0001

Data Index: 182688 (C4 (Web Text))

Max Activating Token Index: 417

Text #17

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0793. Min Act: -0.0001

Data Index: 214094 (C4 (Web Text))

Max Activating Token Index: 625

Text #18

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0669. Min Act: -0.0001

Data Index: 1412705 (Python Code)

Max Activating Token Index: 562

Text #19

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0768. Min Act: -0.0001

Data Index: 714889 (C4 (Web Text))

Max Activating Token Index: 837