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

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

Neuron 3055 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2360. Min Range: -0.2360

Max Act: 0.2360. Min Act: -0.0000

Data Index: 1117518 (C4 (Web Text))

Max Activating Token Index: 544

Text #1

Max Range: 0.2360. Min Range: -0.2360

Max Act: 0.2286. Min Act: -0.0000

Data Index: 17629 (C4 (Web Text))

Max Activating Token Index: 87

Text #2

Max Range: 0.2360. Min Range: -0.2360

Max Act: 0.2040. Min Act: -0.0000

Data Index: 152359 (C4 (Web Text))

Max Activating Token Index: 477

Text #3

Max Range: 0.2360. Min Range: -0.2360

Max Act: 0.1998. Min Act: 0.0000

Data Index: 1124622 (C4 (Web Text))

Max Activating Token Index: 19

Text #4

Max Range: 0.2360. Min Range: -0.2360

Max Act: 0.1964. Min Act: -0.0001

Data Index: 54954 (C4 (Web Text))

Max Activating Token Index: 34

Text #5

Max Range: 0.2360. Min Range: -0.2360

Max Act: 0.1927. Min Act: -0.0001

Data Index: 781624 (C4 (Web Text))

Max Activating Token Index: 199

Text #6

Max Range: 0.2360. Min Range: -0.2360

Max Act: 0.1866. Min Act: -0.0001

Data Index: 430529 (C4 (Web Text))

Max Activating Token Index: 1012

Text #7

Max Range: 0.2360. Min Range: -0.2360

Max Act: 0.1920. Min Act: -0.0000

Data Index: 1301774 (C4 (Web Text))

Max Activating Token Index: 386

Text #8

Max Range: 0.2360. Min Range: -0.2360

Max Act: 0.2030. Min Act: -0.0000

Data Index: 1137769 (C4 (Web Text))

Max Activating Token Index: 861

Text #9

Max Range: 0.2360. Min Range: -0.2360

Max Act: 0.1827. Min Act: -0.0000

Data Index: 371256 (C4 (Web Text))

Max Activating Token Index: 844

Text #10

Max Range: 0.2360. Min Range: -0.2360

Max Act: 0.1863. Min Act: -0.0000

Data Index: 52981 (C4 (Web Text))

Max Activating Token Index: 33

Text #11

Max Range: 0.2360. Min Range: -0.2360

Max Act: 0.1858. Min Act: -0.0000

Data Index: 998233 (C4 (Web Text))

Max Activating Token Index: 66

Text #12

Max Range: 0.2360. Min Range: -0.2360

Max Act: 0.1884. Min Act: -0.0001

Data Index: 981235 (C4 (Web Text))

Max Activating Token Index: 807

Text #13

Max Range: 0.2360. Min Range: -0.2360

Max Act: 0.1744. Min Act: -0.0000

Data Index: 216761 (C4 (Web Text))

Max Activating Token Index: 741

Text #14

Max Range: 0.2360. Min Range: -0.2360

Max Act: 0.1653. Min Act: -0.0000

Data Index: 425334 (C4 (Web Text))

Max Activating Token Index: 769

Text #15

Max Range: 0.2360. Min Range: -0.2360

Max Act: 0.1648. Min Act: -0.0001

Data Index: 283265 (C4 (Web Text))

Max Activating Token Index: 711

Text #16

Max Range: 0.2360. Min Range: -0.2360

Max Act: 0.1663. Min Act: -0.0000

Data Index: 1204408 (C4 (Web Text))

Max Activating Token Index: 996

Text #17

Max Range: 0.2360. Min Range: -0.2360

Max Act: 0.1647. Min Act: 0.0000

Data Index: 1231242 (C4 (Web Text))

Max Activating Token Index: 985

Text #18

Max Range: 0.2360. Min Range: -0.2360

Max Act: 0.1628. Min Act: -0.0000

Data Index: 501387 (C4 (Web Text))

Max Activating Token Index: 732

Text #19

Max Range: 0.2360. Min Range: -0.2360

Max Act: 0.1492. Min Act: -0.0000

Data Index: 1235179 (C4 (Web Text))

Max Activating Token Index: 477