Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2329 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2437. Min Range: -0.2437

Max Act: 0.2437. Min Act: -0.0000

Data Index: 1163767 (C4 (Web Text))

Max Activating Token Index: 448

Text #1

Max Range: 0.2437. Min Range: -0.2437

Max Act: 0.2252. Min Act: -0.0000

Data Index: 1039756 (C4 (Web Text))

Max Activating Token Index: 739

Text #2

Max Range: 0.2437. Min Range: -0.2437

Max Act: 0.2036. Min Act: -0.0001

Data Index: 501900 (C4 (Web Text))

Max Activating Token Index: 245

Text #3

Max Range: 0.2437. Min Range: -0.2437

Max Act: 0.1994. Min Act: -0.0001

Data Index: 826694 (C4 (Web Text))

Max Activating Token Index: 915

Text #4

Max Range: 0.2437. Min Range: -0.2437

Max Act: 0.2090. Min Act: -0.0001

Data Index: 1494672 (Python Code)

Max Activating Token Index: 692

Text #5

Max Range: 0.2437. Min Range: -0.2437

Max Act: 0.1986. Min Act: -0.0000

Data Index: 167264 (C4 (Web Text))

Max Activating Token Index: 951

Text #6

Max Range: 0.2437. Min Range: -0.2437

Max Act: 0.1890. Min Act: -0.0000

Data Index: 488556 (C4 (Web Text))

Max Activating Token Index: 956

Text #7

Max Range: 0.2437. Min Range: -0.2437

Max Act: 0.1894. Min Act: -0.0001

Data Index: 827199 (C4 (Web Text))

Max Activating Token Index: 492

Text #8

Max Range: 0.2437. Min Range: -0.2437

Max Act: 0.1851. Min Act: -0.0001

Data Index: 1475549 (Python Code)

Max Activating Token Index: 587

Text #9

Max Range: 0.2437. Min Range: -0.2437

Max Act: 0.1786. Min Act: -0.0001

Data Index: 718796 (C4 (Web Text))

Max Activating Token Index: 149

Text #10

Max Range: 0.2437. Min Range: -0.2437

Max Act: 0.1817. Min Act: -0.0001

Data Index: 348117 (C4 (Web Text))

Max Activating Token Index: 941

Text #11

Max Range: 0.2437. Min Range: -0.2437

Max Act: 0.1745. Min Act: -0.0001

Data Index: 650135 (C4 (Web Text))

Max Activating Token Index: 614

Text #12

Max Range: 0.2437. Min Range: -0.2437

Max Act: 0.1818. Min Act: -0.0000

Data Index: 83753 (C4 (Web Text))

Max Activating Token Index: 695

Text #13

Max Range: 0.2437. Min Range: -0.2437

Max Act: 0.1754. Min Act: -0.0000

Data Index: 933332 (C4 (Web Text))

Max Activating Token Index: 973

Text #14

Max Range: 0.2437. Min Range: -0.2437

Max Act: 0.1833. Min Act: -0.0000

Data Index: 133290 (C4 (Web Text))

Max Activating Token Index: 983

Text #15

Max Range: 0.2437. Min Range: -0.2437

Max Act: 0.1830. Min Act: -0.0000

Data Index: 933271 (C4 (Web Text))

Max Activating Token Index: 822

Text #16

Max Range: 0.2437. Min Range: -0.2437

Max Act: 0.1758. Min Act: -0.0000

Data Index: 622945 (C4 (Web Text))

Max Activating Token Index: 647

Text #17

Max Range: 0.2437. Min Range: -0.2437

Max Act: 0.1698. Min Act: -0.0001

Data Index: 1508497 (Python Code)

Max Activating Token Index: 295

Text #18

Max Range: 0.2437. Min Range: -0.2437

Max Act: 0.1754. Min Act: -0.0001

Data Index: 568003 (C4 (Web Text))

Max Activating Token Index: 981

Text #19

Max Range: 0.2437. Min Range: -0.2437

Max Act: 0.1630. Min Act: -0.0001

Data Index: 772833 (C4 (Web Text))

Max Activating Token Index: 516