Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 932 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.2902. Min Act: -0.0001

Data Index: 1494288 (Python Code)

Max Activating Token Index: 272

Text #1

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.2190. Min Act: -0.0001

Data Index: 387732 (C4 (Web Text))

Max Activating Token Index: 770

Text #2

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.2200. Min Act: -0.0002

Data Index: 1584706 (Python Code)

Max Activating Token Index: 80

Text #3

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.2205. Min Act: -0.0001

Data Index: 1376310 (Python Code)

Max Activating Token Index: 233

Text #4

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.2193. Min Act: -0.0001

Data Index: 1637514 (Python Code)

Max Activating Token Index: 590

Text #5

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.1980. Min Act: -0.0001

Data Index: 1506430 (Python Code)

Max Activating Token Index: 338

Text #6

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.2129. Min Act: -0.0001

Data Index: 1599715 (Python Code)

Max Activating Token Index: 396

Text #7

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.1884. Min Act: -0.0001

Data Index: 1533154 (Python Code)

Max Activating Token Index: 386

Text #8

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.1913. Min Act: -0.0001

Data Index: 1463116 (Python Code)

Max Activating Token Index: 86

Text #9

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.1813. Min Act: -0.0002

Data Index: 1582191 (Python Code)

Max Activating Token Index: 150

Text #10

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.1971. Min Act: -0.0001

Data Index: 1581966 (Python Code)

Max Activating Token Index: 725

Text #11

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.1761. Min Act: -0.0002

Data Index: 1425595 (Python Code)

Max Activating Token Index: 292

Text #12

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.1887. Min Act: -0.0001

Data Index: 1641996 (Python Code)

Max Activating Token Index: 637

Text #13

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.1801. Min Act: -0.0001

Data Index: 1422776 (Python Code)

Max Activating Token Index: 23

Text #14

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.1835. Min Act: -0.0001

Data Index: 1633461 (Python Code)

Max Activating Token Index: 16

Text #15

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.1889. Min Act: -0.0001

Data Index: 1451492 (Python Code)

Max Activating Token Index: 20

Text #16

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.1848. Min Act: -0.0001

Data Index: 1383990 (Python Code)

Max Activating Token Index: 978

Text #17

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.1886. Min Act: -0.0001

Data Index: 1650392 (Python Code)

Max Activating Token Index: 72

Text #18

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.1720. Min Act: -0.0001

Data Index: 1508536 (Python Code)

Max Activating Token Index: 172

Text #19

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.1713. Min Act: -0.0001

Data Index: 1562537 (Python Code)

Max Activating Token Index: 147