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

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

Neuron 4303 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.2815. Min Range: -0.2815

Max Act: 0.2750. Min Act: -0.0000

Data Index: 1616450 (Python Code)

Max Activating Token Index: 75

Text #1

Max Range: 0.2815. Min Range: -0.2815

Max Act: 0.2815. Min Act: -0.0000

Data Index: 1481021 (Python Code)

Max Activating Token Index: 250

Text #2

Max Range: 0.2815. Min Range: -0.2815

Max Act: 0.2697. Min Act: -0.0000

Data Index: 1435770 (Python Code)

Max Activating Token Index: 547

Text #3

Max Range: 0.2815. Min Range: -0.2815

Max Act: 0.2417. Min Act: -0.0000

Data Index: 1531879 (Python Code)

Max Activating Token Index: 482

Text #4

Max Range: 0.2815. Min Range: -0.2815

Max Act: 0.2326. Min Act: -0.0000

Data Index: 1429773 (Python Code)

Max Activating Token Index: 353

Text #5

Max Range: 0.2815. Min Range: -0.2815

Max Act: 0.2284. Min Act: -0.0000

Data Index: 1388582 (Python Code)

Max Activating Token Index: 966

Text #6

Max Range: 0.2815. Min Range: -0.2815

Max Act: 0.2500. Min Act: -0.0000

Data Index: 1365766 (Python Code)

Max Activating Token Index: 673

Text #7

Max Range: 0.2815. Min Range: -0.2815

Max Act: 0.2371. Min Act: -0.0000

Data Index: 1543003 (Python Code)

Max Activating Token Index: 455

Text #8

Max Range: 0.2815. Min Range: -0.2815

Max Act: 0.2214. Min Act: -0.0000

Data Index: 1540406 (Python Code)

Max Activating Token Index: 276

Text #9

Max Range: 0.2815. Min Range: -0.2815

Max Act: 0.2013. Min Act: -0.0000

Data Index: 1634894 (Python Code)

Max Activating Token Index: 174

Text #10

Max Range: 0.2815. Min Range: -0.2815

Max Act: 0.2149. Min Act: -0.0000

Data Index: 1628497 (Python Code)

Max Activating Token Index: 136

Text #11

Max Range: 0.2815. Min Range: -0.2815

Max Act: 0.2203. Min Act: -0.0000

Data Index: 1407882 (Python Code)

Max Activating Token Index: 821

Text #12

Max Range: 0.2815. Min Range: -0.2815

Max Act: 0.2037. Min Act: -0.0000

Data Index: 1451877 (Python Code)

Max Activating Token Index: 932

Text #13

Max Range: 0.2815. Min Range: -0.2815

Max Act: 0.2027. Min Act: -0.0000

Data Index: 1597370 (Python Code)

Max Activating Token Index: 137

Text #14

Max Range: 0.2815. Min Range: -0.2815

Max Act: 0.2121. Min Act: -0.0000

Data Index: 1501312 (Python Code)

Max Activating Token Index: 531

Text #15

Max Range: 0.2815. Min Range: -0.2815

Max Act: 0.1966. Min Act: -0.0000

Data Index: 1635563 (Python Code)

Max Activating Token Index: 688

Text #16

Max Range: 0.2815. Min Range: -0.2815

Max Act: 0.1945. Min Act: -0.0000

Data Index: 1526206 (Python Code)

Max Activating Token Index: 395

Text #17

Max Range: 0.2815. Min Range: -0.2815

Max Act: 0.2004. Min Act: -0.0000

Data Index: 1403970 (Python Code)

Max Activating Token Index: 886

Text #18

Max Range: 0.2815. Min Range: -0.2815

Max Act: 0.2055. Min Act: -0.0000

Data Index: 1553588 (Python Code)

Max Activating Token Index: 931

Text #19

Max Range: 0.2815. Min Range: -0.2815

Max Act: 0.2020. Min Act: -0.0000

Data Index: 1453792 (Python Code)

Max Activating Token Index: 188