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

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

Neuron 1674 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: 0.3980. Min Range: -0.3980

Max Act: 0.3980. Min Act: -0.0000

Data Index: 702475 (C4 (Web Text))

Max Activating Token Index: 613

Text #1

Max Range: 0.3980. Min Range: -0.3980

Max Act: 0.2039. Min Act: -0.0000

Data Index: 867765 (C4 (Web Text))

Max Activating Token Index: 99

Text #2

Max Range: 0.3980. Min Range: -0.3980

Max Act: 0.1906. Min Act: -0.0000

Data Index: 997105 (C4 (Web Text))

Max Activating Token Index: 883

Text #3

Max Range: 0.3980. Min Range: -0.3980

Max Act: 0.1963. Min Act: -0.0000

Data Index: 739066 (C4 (Web Text))

Max Activating Token Index: 690

Text #4

Max Range: 0.3980. Min Range: -0.3980

Max Act: 0.1884. Min Act: -0.0000

Data Index: 891155 (C4 (Web Text))

Max Activating Token Index: 846

Text #5

Max Range: 0.3980. Min Range: -0.3980

Max Act: 0.1853. Min Act: -0.0000

Data Index: 192112 (C4 (Web Text))

Max Activating Token Index: 574

Text #6

Max Range: 0.3980. Min Range: -0.3980

Max Act: 0.1749. Min Act: -0.0000

Data Index: 296061 (C4 (Web Text))

Max Activating Token Index: 987

Text #7

Max Range: 0.3980. Min Range: -0.3980

Max Act: 0.1699. Min Act: -0.0000

Data Index: 467486 (C4 (Web Text))

Max Activating Token Index: 971

Text #8

Max Range: 0.3980. Min Range: -0.3980

Max Act: 0.1607. Min Act: -0.0000

Data Index: 966905 (C4 (Web Text))

Max Activating Token Index: 647

Text #9

Max Range: 0.3980. Min Range: -0.3980

Max Act: 0.1712. Min Act: -0.0000

Data Index: 1114370 (C4 (Web Text))

Max Activating Token Index: 935

Text #10

Max Range: 0.3980. Min Range: -0.3980

Max Act: 0.1588. Min Act: -0.0000

Data Index: 1325559 (C4 (Web Text))

Max Activating Token Index: 841

Text #11

Max Range: 0.3980. Min Range: -0.3980

Max Act: 0.1610. Min Act: -0.0000

Data Index: 441855 (C4 (Web Text))

Max Activating Token Index: 984

Text #12

Max Range: 0.3980. Min Range: -0.3980

Max Act: 0.1713. Min Act: -0.0000

Data Index: 820637 (C4 (Web Text))

Max Activating Token Index: 1002

Text #13

Max Range: 0.3980. Min Range: -0.3980

Max Act: 0.1708. Min Act: -0.0000

Data Index: 1111707 (C4 (Web Text))

Max Activating Token Index: 996

Text #14

Max Range: 0.3980. Min Range: -0.3980

Max Act: 0.1593. Min Act: -0.0000

Data Index: 999895 (C4 (Web Text))

Max Activating Token Index: 525

Text #15

Max Range: 0.3980. Min Range: -0.3980

Max Act: 0.1552. Min Act: -0.0000

Data Index: 310773 (C4 (Web Text))

Max Activating Token Index: 825

Text #16

Max Range: 0.3980. Min Range: -0.3980

Max Act: 0.1531. Min Act: -0.0000

Data Index: 617366 (C4 (Web Text))

Max Activating Token Index: 966

Text #17

Max Range: 0.3980. Min Range: -0.3980

Max Act: 0.1556. Min Act: -0.0000

Data Index: 23165 (C4 (Web Text))

Max Activating Token Index: 300

Text #18

Max Range: 0.3980. Min Range: -0.3980

Max Act: 0.1542. Min Act: -0.0000

Data Index: 116595 (C4 (Web Text))

Max Activating Token Index: 102

Text #19

Max Range: 0.3980. Min Range: -0.3980

Max Act: 0.1528. Min Act: -0.0000

Data Index: 28785 (C4 (Web Text))

Max Activating Token Index: 339