Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 465 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 5.1338. Min Range: -5.1338

Max Act: 5.1338. Min Act: -0.1700

Data Index: 1580052 (Python Code)

Max Activating Token Index: 22

Text #1

Max Range: 5.1338. Min Range: -5.1338

Max Act: 5.1026. Min Act: -0.1700

Data Index: 1570241 (Python Code)

Max Activating Token Index: 676

Text #2

Max Range: 5.1338. Min Range: -5.1338

Max Act: 5.0401. Min Act: -0.1700

Data Index: 1417699 (Python Code)

Max Activating Token Index: 638

Text #3

Max Range: 5.1338. Min Range: -5.1338

Max Act: 5.0713. Min Act: -0.1700

Data Index: 1451919 (Python Code)

Max Activating Token Index: 632

Text #4

Max Range: 5.1338. Min Range: -5.1338

Max Act: 4.9776. Min Act: -0.1700

Data Index: 1377913 (Python Code)

Max Activating Token Index: 815

Text #5

Max Range: 5.1338. Min Range: -5.1338

Max Act: 5.0088. Min Act: -0.1700

Data Index: 1436255 (Python Code)

Max Activating Token Index: 780

Text #6

Max Range: 5.1338. Min Range: -5.1338

Max Act: 4.9463. Min Act: -0.1700

Data Index: 1375817 (Python Code)

Max Activating Token Index: 689

Text #7

Max Range: 5.1338. Min Range: -5.1338

Max Act: 4.9463. Min Act: -0.1700

Data Index: 1651587 (Python Code)

Max Activating Token Index: 45

Text #8

Max Range: 5.1338. Min Range: -5.1338

Max Act: 4.9776. Min Act: -0.1700

Data Index: 1578153 (Python Code)

Max Activating Token Index: 504

Text #9

Max Range: 5.1338. Min Range: -5.1338

Max Act: 4.9463. Min Act: -0.1700

Data Index: 1469929 (Python Code)

Max Activating Token Index: 13

Text #10

Max Range: 5.1338. Min Range: -5.1338

Max Act: 4.9463. Min Act: -0.1700

Data Index: 1529190 (Python Code)

Max Activating Token Index: 11

Text #11

Max Range: 5.1338. Min Range: -5.1338

Max Act: 4.9776. Min Act: -0.1700

Data Index: 1385296 (Python Code)

Max Activating Token Index: 781

Text #12

Max Range: 5.1338. Min Range: -5.1338

Max Act: 4.9463. Min Act: -0.1700

Data Index: 1436169 (Python Code)

Max Activating Token Index: 600

Text #13

Max Range: 5.1338. Min Range: -5.1338

Max Act: 4.9151. Min Act: -0.1700

Data Index: 1396742 (Python Code)

Max Activating Token Index: 835

Text #14

Max Range: 5.1338. Min Range: -5.1338

Max Act: 4.9151. Min Act: -0.1700

Data Index: 1505536 (Python Code)

Max Activating Token Index: 39

Text #15

Max Range: 5.1338. Min Range: -5.1338

Max Act: 4.9776. Min Act: -0.1700

Data Index: 1491048 (Python Code)

Max Activating Token Index: 898

Text #16

Max Range: 5.1338. Min Range: -5.1338

Max Act: 4.9151. Min Act: -0.1700

Data Index: 1592244 (Python Code)

Max Activating Token Index: 758

Text #17

Max Range: 5.1338. Min Range: -5.1338

Max Act: 4.9151. Min Act: -0.1700

Data Index: 1404513 (Python Code)

Max Activating Token Index: 615

Text #18

Max Range: 5.1338. Min Range: -5.1338

Max Act: 4.8838. Min Act: -0.1700

Data Index: 1596775 (Python Code)

Max Activating Token Index: 625

Text #19

Max Range: 5.1338. Min Range: -5.1338

Max Act: 4.9151. Min Act: -0.1700

Data Index: 1534950 (Python Code)

Max Activating Token Index: 69