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

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

Neuron 518 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: 0.2260. Min Range: -0.2260

Max Act: 0.2260. Min Act: -0.0001

Data Index: 300963 (C4 (Web Text))

Max Activating Token Index: 631

Text #1

Max Range: 0.2260. Min Range: -0.2260

Max Act: 0.1798. Min Act: -0.0001

Data Index: 27259 (C4 (Web Text))

Max Activating Token Index: 574

Text #2

Max Range: 0.2260. Min Range: -0.2260

Max Act: 0.1793. Min Act: -0.0001

Data Index: 1313667 (C4 (Web Text))

Max Activating Token Index: 937

Text #3

Max Range: 0.2260. Min Range: -0.2260

Max Act: 0.1879. Min Act: -0.0001

Data Index: 1051795 (C4 (Web Text))

Max Activating Token Index: 191

Text #4

Max Range: 0.2260. Min Range: -0.2260

Max Act: 0.1849. Min Act: -0.0001

Data Index: 996379 (C4 (Web Text))

Max Activating Token Index: 984

Text #5

Max Range: 0.2260. Min Range: -0.2260

Max Act: 0.1851. Min Act: -0.0001

Data Index: 909163 (C4 (Web Text))

Max Activating Token Index: 940

Text #6

Max Range: 0.2260. Min Range: -0.2260

Max Act: 0.1919. Min Act: -0.0000

Data Index: 611063 (C4 (Web Text))

Max Activating Token Index: 667

Text #7

Max Range: 0.2260. Min Range: -0.2260

Max Act: 0.1774. Min Act: -0.0001

Data Index: 481915 (C4 (Web Text))

Max Activating Token Index: 985

Text #8

Max Range: 0.2260. Min Range: -0.2260

Max Act: 0.1836. Min Act: -0.0001

Data Index: 910041 (C4 (Web Text))

Max Activating Token Index: 949

Text #9

Max Range: 0.2260. Min Range: -0.2260

Max Act: 0.1826. Min Act: -0.0001

Data Index: 1174417 (C4 (Web Text))

Max Activating Token Index: 714

Text #10

Max Range: 0.2260. Min Range: -0.2260

Max Act: 0.1936. Min Act: -0.0001

Data Index: 519608 (C4 (Web Text))

Max Activating Token Index: 611

Text #11

Max Range: 0.2260. Min Range: -0.2260

Max Act: 0.1800. Min Act: -0.0001

Data Index: 1183840 (C4 (Web Text))

Max Activating Token Index: 826

Text #12

Max Range: 0.2260. Min Range: -0.2260

Max Act: 0.1801. Min Act: -0.0001

Data Index: 942684 (C4 (Web Text))

Max Activating Token Index: 838

Text #13

Max Range: 0.2260. Min Range: -0.2260

Max Act: 0.1858. Min Act: -0.0001

Data Index: 880055 (C4 (Web Text))

Max Activating Token Index: 103

Text #14

Max Range: 0.2260. Min Range: -0.2260

Max Act: 0.1848. Min Act: -0.0001

Data Index: 767435 (C4 (Web Text))

Max Activating Token Index: 611

Text #15

Max Range: 0.2260. Min Range: -0.2260

Max Act: 0.1629. Min Act: -0.0001

Data Index: 697334 (C4 (Web Text))

Max Activating Token Index: 314

Text #16

Max Range: 0.2260. Min Range: -0.2260

Max Act: 0.1724. Min Act: -0.0001

Data Index: 906545 (C4 (Web Text))

Max Activating Token Index: 966

Text #17

Max Range: 0.2260. Min Range: -0.2260

Max Act: 0.1748. Min Act: -0.0001

Data Index: 960261 (C4 (Web Text))

Max Activating Token Index: 607

Text #18

Max Range: 0.2260. Min Range: -0.2260

Max Act: 0.1819. Min Act: -0.0000

Data Index: 1146542 (C4 (Web Text))

Max Activating Token Index: 372

Text #19

Max Range: 0.2260. Min Range: -0.2260

Max Act: 0.1819. Min Act: -0.0001

Data Index: 255073 (C4 (Web Text))

Max Activating Token Index: 983