Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2219 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0825. Min Act: -0.0001

Data Index: 1586326 (Python Code)

Max Activating Token Index: 546

Text #1

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0765. Min Act: -0.0001

Data Index: 1526537 (Python Code)

Max Activating Token Index: 501

Text #2

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0744. Min Act: -0.0001

Data Index: 1543649 (Python Code)

Max Activating Token Index: 83

Text #3

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0758. Min Act: -0.0001

Data Index: 1422970 (Python Code)

Max Activating Token Index: 827

Text #4

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0765. Min Act: -0.0001

Data Index: 793074 (C4 (Web Text))

Max Activating Token Index: 66

Text #5

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0709. Min Act: -0.0001

Data Index: 399224 (C4 (Web Text))

Max Activating Token Index: 749

Text #6

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0721. Min Act: -0.0001

Data Index: 1533841 (Python Code)

Max Activating Token Index: 29

Text #7

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0743. Min Act: -0.0001

Data Index: 486795 (C4 (Web Text))

Max Activating Token Index: 657

Text #8

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0722. Min Act: -0.0001

Data Index: 1374023 (Python Code)

Max Activating Token Index: 430

Text #9

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0693. Min Act: -0.0001

Data Index: 1615800 (Python Code)

Max Activating Token Index: 97

Text #10

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0684. Min Act: -0.0001

Data Index: 1566956 (Python Code)

Max Activating Token Index: 468

Text #11

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0697. Min Act: -0.0001

Data Index: 514189 (C4 (Web Text))

Max Activating Token Index: 9

Text #12

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0670. Min Act: -0.0001

Data Index: 1389488 (Python Code)

Max Activating Token Index: 1020

Text #13

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0664. Min Act: -0.0001

Data Index: 1529644 (Python Code)

Max Activating Token Index: 30

Text #14

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0668. Min Act: -0.0001

Data Index: 1570434 (Python Code)

Max Activating Token Index: 975

Text #15

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0683. Min Act: -0.0001

Data Index: 1063049 (C4 (Web Text))

Max Activating Token Index: 700

Text #16

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0661. Min Act: -0.0001

Data Index: 1596027 (Python Code)

Max Activating Token Index: 229

Text #17

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0665. Min Act: -0.0001

Data Index: 998530 (C4 (Web Text))

Max Activating Token Index: 508

Text #18

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0685. Min Act: -0.0001

Data Index: 1154421 (C4 (Web Text))

Max Activating Token Index: 273

Text #19

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0647. Min Act: -0.0001

Data Index: 1182564 (C4 (Web Text))

Max Activating Token Index: 986