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

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

Neuron 1019 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0881. Min Range: -0.0881

Max Act: 0.0881. Min Act: -0.0000

Data Index: 1008681 (C4 (Web Text))

Max Activating Token Index: 889

Text #1

Max Range: 0.0881. Min Range: -0.0881

Max Act: 0.0780. Min Act: -0.0000

Data Index: 283457 (C4 (Web Text))

Max Activating Token Index: 647

Text #2

Max Range: 0.0881. Min Range: -0.0881

Max Act: 0.0738. Min Act: -0.0000

Data Index: 380333 (C4 (Web Text))

Max Activating Token Index: 248

Text #3

Max Range: 0.0881. Min Range: -0.0881

Max Act: 0.0705. Min Act: -0.0000

Data Index: 33621 (C4 (Web Text))

Max Activating Token Index: 961

Text #4

Max Range: 0.0881. Min Range: -0.0881

Max Act: 0.0768. Min Act: -0.0000

Data Index: 1117938 (C4 (Web Text))

Max Activating Token Index: 606

Text #5

Max Range: 0.0881. Min Range: -0.0881

Max Act: 0.0673. Min Act: -0.0000

Data Index: 191961 (C4 (Web Text))

Max Activating Token Index: 860

Text #6

Max Range: 0.0881. Min Range: -0.0881

Max Act: 0.0626. Min Act: -0.0000

Data Index: 826206 (C4 (Web Text))

Max Activating Token Index: 700

Text #7

Max Range: 0.0881. Min Range: -0.0881

Max Act: 0.0682. Min Act: -0.0000

Data Index: 1231956 (C4 (Web Text))

Max Activating Token Index: 749

Text #8

Max Range: 0.0881. Min Range: -0.0881

Max Act: 0.0639. Min Act: -0.0000

Data Index: 263679 (C4 (Web Text))

Max Activating Token Index: 486

Text #9

Max Range: 0.0881. Min Range: -0.0881

Max Act: 0.0675. Min Act: -0.0000

Data Index: 303352 (C4 (Web Text))

Max Activating Token Index: 689

Text #10

Max Range: 0.0881. Min Range: -0.0881

Max Act: 0.0602. Min Act: -0.0000

Data Index: 295417 (C4 (Web Text))

Max Activating Token Index: 140

Text #11

Max Range: 0.0881. Min Range: -0.0881

Max Act: 0.0640. Min Act: -0.0000

Data Index: 354704 (C4 (Web Text))

Max Activating Token Index: 199

Text #12

Max Range: 0.0881. Min Range: -0.0881

Max Act: 0.0607. Min Act: -0.0000

Data Index: 1628339 (Python Code)

Max Activating Token Index: 564

Text #13

Max Range: 0.0881. Min Range: -0.0881

Max Act: 0.0559. Min Act: -0.0000

Data Index: 653841 (C4 (Web Text))

Max Activating Token Index: 474

Text #14

Max Range: 0.0881. Min Range: -0.0881

Max Act: 0.0576. Min Act: -0.0000

Data Index: 837151 (C4 (Web Text))

Max Activating Token Index: 788

Text #15

Max Range: 0.0881. Min Range: -0.0881

Max Act: 0.0574. Min Act: -0.0000

Data Index: 1354995 (C4 (Web Text))

Max Activating Token Index: 713

Text #16

Max Range: 0.0881. Min Range: -0.0881

Max Act: 0.0585. Min Act: -0.0000

Data Index: 255006 (C4 (Web Text))

Max Activating Token Index: 752

Text #17

Max Range: 0.0881. Min Range: -0.0881

Max Act: 0.0540. Min Act: -0.0000

Data Index: 137294 (C4 (Web Text))

Max Activating Token Index: 1019

Text #18

Max Range: 0.0881. Min Range: -0.0881

Max Act: 0.0558. Min Act: -0.0000

Data Index: 1041520 (C4 (Web Text))

Max Activating Token Index: 190

Text #19

Max Range: 0.0881. Min Range: -0.0881

Max Act: 0.0547. Min Act: -0.0000

Data Index: 104793 (C4 (Web Text))

Max Activating Token Index: 324