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

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

Neuron 3964 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2386. Min Range: -2.2386

Max Act: 2.2386. Min Act: -0.0000

Data Index: 1559488 (Python Code)

Max Activating Token Index: 621

Text #1

Max Range: 2.2386. Min Range: -2.2386

Max Act: 2.0870. Min Act: -0.0000

Data Index: 1556824 (Python Code)

Max Activating Token Index: 669

Text #2

Max Range: 2.2386. Min Range: -2.2386

Max Act: 2.2023. Min Act: -0.0000

Data Index: 1371571 (Python Code)

Max Activating Token Index: 231

Text #3

Max Range: 2.2386. Min Range: -2.2386

Max Act: 2.1307. Min Act: -0.0000

Data Index: 1565138 (Python Code)

Max Activating Token Index: 393

Text #4

Max Range: 2.2386. Min Range: -2.2386

Max Act: 1.9968. Min Act: -0.0000

Data Index: 1591850 (Python Code)

Max Activating Token Index: 86

Text #5

Max Range: 2.2386. Min Range: -2.2386

Max Act: 2.0776. Min Act: -0.0000

Data Index: 1522461 (Python Code)

Max Activating Token Index: 32

Text #6

Max Range: 2.2386. Min Range: -2.2386

Max Act: 1.9519. Min Act: -0.0000

Data Index: 1446665 (Python Code)

Max Activating Token Index: 598

Text #7

Max Range: 2.2386. Min Range: -2.2386

Max Act: 1.8807. Min Act: -0.0000

Data Index: 1546796 (Python Code)

Max Activating Token Index: 818

Text #8

Max Range: 2.2386. Min Range: -2.2386

Max Act: 1.8412. Min Act: -0.0000

Data Index: 1557082 (Python Code)

Max Activating Token Index: 372

Text #9

Max Range: 2.2386. Min Range: -2.2386

Max Act: 1.8367. Min Act: -0.0000

Data Index: 1473157 (Python Code)

Max Activating Token Index: 946

Text #10

Max Range: 2.2386. Min Range: -2.2386

Max Act: 1.8281. Min Act: -0.0000

Data Index: 1556757 (Python Code)

Max Activating Token Index: 707

Text #11

Max Range: 2.2386. Min Range: -2.2386

Max Act: 1.8105. Min Act: -0.0000

Data Index: 1613126 (Python Code)

Max Activating Token Index: 385

Text #12

Max Range: 2.2386. Min Range: -2.2386

Max Act: 1.7969. Min Act: -0.0000

Data Index: 1570808 (Python Code)

Max Activating Token Index: 305

Text #13

Max Range: 2.2386. Min Range: -2.2386

Max Act: 1.7481. Min Act: -0.0000

Data Index: 1544143 (Python Code)

Max Activating Token Index: 732

Text #14

Max Range: 2.2386. Min Range: -2.2386

Max Act: 1.7107. Min Act: -0.0000

Data Index: 1509242 (Python Code)

Max Activating Token Index: 638

Text #15

Max Range: 2.2386. Min Range: -2.2386

Max Act: 1.6945. Min Act: -0.0000

Data Index: 1567130 (Python Code)

Max Activating Token Index: 173

Text #16

Max Range: 2.2386. Min Range: -2.2386

Max Act: 1.7813. Min Act: -0.0000

Data Index: 1361981 (Python Code)

Max Activating Token Index: 631

Text #17

Max Range: 2.2386. Min Range: -2.2386

Max Act: 1.7839. Min Act: -0.0000

Data Index: 1641624 (Python Code)

Max Activating Token Index: 350

Text #18

Max Range: 2.2386. Min Range: -2.2386

Max Act: 1.5828. Min Act: -0.0000

Data Index: 1466615 (Python Code)

Max Activating Token Index: 732

Text #19

Max Range: 2.2386. Min Range: -2.2386

Max Act: 1.8845. Min Act: -0.0000

Data Index: 1622876 (Python Code)

Max Activating Token Index: 693