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

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

Neuron 4548 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3612. Min Range: -1.3612

Max Act: 1.2573. Min Act: -0.0001

Data Index: 1523238 (Python Code)

Max Activating Token Index: 729

Text #1

Max Range: 1.3612. Min Range: -1.3612

Max Act: 1.3612. Min Act: -0.0001

Data Index: 1647446 (Python Code)

Max Activating Token Index: 915

Text #2

Max Range: 1.3612. Min Range: -1.3612

Max Act: 1.2275. Min Act: -0.0001

Data Index: 1459271 (Python Code)

Max Activating Token Index: 22

Text #3

Max Range: 1.3612. Min Range: -1.3612

Max Act: 1.0733. Min Act: -0.0001

Data Index: 1617871 (Python Code)

Max Activating Token Index: 132

Text #4

Max Range: 1.3612. Min Range: -1.3612

Max Act: 1.1952. Min Act: -0.0001

Data Index: 1505613 (Python Code)

Max Activating Token Index: 319

Text #5

Max Range: 1.3612. Min Range: -1.3612

Max Act: 1.1767. Min Act: -0.0001

Data Index: 1542644 (Python Code)

Max Activating Token Index: 625

Text #6

Max Range: 1.3612. Min Range: -1.3612

Max Act: 0.9193. Min Act: -0.0001

Data Index: 1545596 (Python Code)

Max Activating Token Index: 746

Text #7

Max Range: 1.3612. Min Range: -1.3612

Max Act: 0.9337. Min Act: -0.0001

Data Index: 1439686 (Python Code)

Max Activating Token Index: 790

Text #8

Max Range: 1.3612. Min Range: -1.3612

Max Act: 1.0503. Min Act: -0.0001

Data Index: 1593394 (Python Code)

Max Activating Token Index: 879

Text #9

Max Range: 1.3612. Min Range: -1.3612

Max Act: 1.0278. Min Act: -0.0001

Data Index: 1438662 (Python Code)

Max Activating Token Index: 157

Text #10

Max Range: 1.3612. Min Range: -1.3612

Max Act: 0.9634. Min Act: -0.0001

Data Index: 1490037 (Python Code)

Max Activating Token Index: 104

Text #11

Max Range: 1.3612. Min Range: -1.3612

Max Act: 0.9743. Min Act: -0.0001

Data Index: 1605253 (Python Code)

Max Activating Token Index: 341

Text #12

Max Range: 1.3612. Min Range: -1.3612

Max Act: 0.8824. Min Act: -0.0001

Data Index: 1445081 (Python Code)

Max Activating Token Index: 844

Text #13

Max Range: 1.3612. Min Range: -1.3612

Max Act: 0.9038. Min Act: -0.0001

Data Index: 1423886 (Python Code)

Max Activating Token Index: 884

Text #14

Max Range: 1.3612. Min Range: -1.3612

Max Act: 0.8529. Min Act: -0.0001

Data Index: 1440311 (Python Code)

Max Activating Token Index: 871

Text #15

Max Range: 1.3612. Min Range: -1.3612

Max Act: 0.9301. Min Act: -0.0001

Data Index: 1555907 (Python Code)

Max Activating Token Index: 842

Text #16

Max Range: 1.3612. Min Range: -1.3612

Max Act: 0.8693. Min Act: -0.0001

Data Index: 1626786 (Python Code)

Max Activating Token Index: 704

Text #17

Max Range: 1.3612. Min Range: -1.3612

Max Act: 0.9343. Min Act: -0.0001

Data Index: 1553011 (Python Code)

Max Activating Token Index: 790

Text #18

Max Range: 1.3612. Min Range: -1.3612

Max Act: 0.8779. Min Act: -0.0001

Data Index: 1423067 (Python Code)

Max Activating Token Index: 429

Text #19

Max Range: 1.3612. Min Range: -1.3612

Max Act: 0.8167. Min Act: -0.0001

Data Index: 1554422 (Python Code)

Max Activating Token Index: 749