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

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

Neuron 3368 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: 0.2353. Min Range: -0.2353

Max Act: 0.2342. Min Act: -0.0000

Data Index: 1223147 (C4 (Web Text))

Max Activating Token Index: 1001

Text #1

Max Range: 0.2353. Min Range: -0.2353

Max Act: 0.2350. Min Act: -0.0000

Data Index: 8420 (C4 (Web Text))

Max Activating Token Index: 772

Text #2

Max Range: 0.2353. Min Range: -0.2353

Max Act: 0.2252. Min Act: -0.0000

Data Index: 997235 (C4 (Web Text))

Max Activating Token Index: 980

Text #3

Max Range: 0.2353. Min Range: -0.2353

Max Act: 0.2353. Min Act: -0.0000

Data Index: 1029994 (C4 (Web Text))

Max Activating Token Index: 957

Text #4

Max Range: 0.2353. Min Range: -0.2353

Max Act: 0.2246. Min Act: -0.0000

Data Index: 1168502 (C4 (Web Text))

Max Activating Token Index: 946

Text #5

Max Range: 0.2353. Min Range: -0.2353

Max Act: 0.2168. Min Act: -0.0000

Data Index: 345875 (C4 (Web Text))

Max Activating Token Index: 994

Text #6

Max Range: 0.2353. Min Range: -0.2353

Max Act: 0.2106. Min Act: -0.0000

Data Index: 1115777 (C4 (Web Text))

Max Activating Token Index: 842

Text #7

Max Range: 0.2353. Min Range: -0.2353

Max Act: 0.2253. Min Act: -0.0000

Data Index: 880473 (C4 (Web Text))

Max Activating Token Index: 1019

Text #8

Max Range: 0.2353. Min Range: -0.2353

Max Act: 0.2061. Min Act: -0.0000

Data Index: 482055 (C4 (Web Text))

Max Activating Token Index: 515

Text #9

Max Range: 0.2353. Min Range: -0.2353

Max Act: 0.2144. Min Act: -0.0000

Data Index: 957039 (C4 (Web Text))

Max Activating Token Index: 143

Text #10

Max Range: 0.2353. Min Range: -0.2353

Max Act: 0.1970. Min Act: -0.0000

Data Index: 1038889 (C4 (Web Text))

Max Activating Token Index: 629

Text #11

Max Range: 0.2353. Min Range: -0.2353

Max Act: 0.2023. Min Act: -0.0000

Data Index: 544812 (C4 (Web Text))

Max Activating Token Index: 704

Text #12

Max Range: 0.2353. Min Range: -0.2353

Max Act: 0.2185. Min Act: -0.0000

Data Index: 319433 (C4 (Web Text))

Max Activating Token Index: 196

Text #13

Max Range: 0.2353. Min Range: -0.2353

Max Act: 0.1888. Min Act: -0.0000

Data Index: 837580 (C4 (Web Text))

Max Activating Token Index: 185

Text #14

Max Range: 0.2353. Min Range: -0.2353

Max Act: 0.1894. Min Act: -0.0000

Data Index: 632266 (C4 (Web Text))

Max Activating Token Index: 638

Text #15

Max Range: 0.2353. Min Range: -0.2353

Max Act: 0.1812. Min Act: -0.0000

Data Index: 1320424 (C4 (Web Text))

Max Activating Token Index: 55

Text #16

Max Range: 0.2353. Min Range: -0.2353

Max Act: 0.1795. Min Act: -0.0000

Data Index: 13126 (C4 (Web Text))

Max Activating Token Index: 495

Text #17

Max Range: 0.2353. Min Range: -0.2353

Max Act: 0.1730. Min Act: -0.0000

Data Index: 55009 (C4 (Web Text))

Max Activating Token Index: 130

Text #18

Max Range: 0.2353. Min Range: -0.2353

Max Act: 0.1706. Min Act: -0.0000

Data Index: 759948 (C4 (Web Text))

Max Activating Token Index: 260

Text #19

Max Range: 0.2353. Min Range: -0.2353

Max Act: 0.1741. Min Act: -0.0000

Data Index: 58689 (C4 (Web Text))

Max Activating Token Index: 38