Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 1825 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 3.4678. Min Range: -3.4678

Max Act: 3.4678. Min Act: -0.1700

Data Index: 1540191 (Python Code)

Max Activating Token Index: 595

Text #1

Max Range: 3.4678. Min Range: -3.4678

Max Act: 3.3441. Min Act: -0.1700

Data Index: 1396708 (Python Code)

Max Activating Token Index: 973

Text #2

Max Range: 3.4678. Min Range: -3.4678

Max Act: 3.2734. Min Act: -0.1700

Data Index: 1395483 (Python Code)

Max Activating Token Index: 544

Text #3

Max Range: 3.4678. Min Range: -3.4678

Max Act: 3.2453. Min Act: -0.1698

Data Index: 1495401 (Python Code)

Max Activating Token Index: 804

Text #4

Max Range: 3.4678. Min Range: -3.4678

Max Act: 3.2246. Min Act: -0.1700

Data Index: 1506807 (Python Code)

Max Activating Token Index: 867

Text #5

Max Range: 3.4678. Min Range: -3.4678

Max Act: 3.1743. Min Act: -0.1700

Data Index: 1488076 (Python Code)

Max Activating Token Index: 708

Text #6

Max Range: 3.4678. Min Range: -3.4678

Max Act: 3.1840. Min Act: -0.1700

Data Index: 1570105 (Python Code)

Max Activating Token Index: 768

Text #7

Max Range: 3.4678. Min Range: -3.4678

Max Act: 3.2066. Min Act: -0.1700

Data Index: 1497433 (Python Code)

Max Activating Token Index: 843

Text #8

Max Range: 3.4678. Min Range: -3.4678

Max Act: 3.1571. Min Act: -0.1699

Data Index: 1619502 (Python Code)

Max Activating Token Index: 981

Text #9

Max Range: 3.4678. Min Range: -3.4678

Max Act: 3.1170. Min Act: -0.1700

Data Index: 1561749 (Python Code)

Max Activating Token Index: 556

Text #10

Max Range: 3.4678. Min Range: -3.4678

Max Act: 3.1315. Min Act: -0.1700

Data Index: 1396171 (Python Code)

Max Activating Token Index: 173

Text #11

Max Range: 3.4678. Min Range: -3.4678

Max Act: 3.1269. Min Act: -0.1700

Data Index: 1576528 (Python Code)

Max Activating Token Index: 890

Text #12

Max Range: 3.4678. Min Range: -3.4678

Max Act: 3.1280. Min Act: -0.1700

Data Index: 1534394 (Python Code)

Max Activating Token Index: 481

Text #13

Max Range: 3.4678. Min Range: -3.4678

Max Act: 3.1405. Min Act: -0.1698

Data Index: 1630486 (Python Code)

Max Activating Token Index: 654

Text #14

Max Range: 3.4678. Min Range: -3.4678

Max Act: 3.0994. Min Act: -0.1700

Data Index: 1618238 (Python Code)

Max Activating Token Index: 285

Text #15

Max Range: 3.4678. Min Range: -3.4678

Max Act: 3.0779. Min Act: -0.1699

Data Index: 1504267 (Python Code)

Max Activating Token Index: 734

Text #16

Max Range: 3.4678. Min Range: -3.4678

Max Act: 3.0739. Min Act: -0.1699

Data Index: 1396050 (Python Code)

Max Activating Token Index: 944

Text #17

Max Range: 3.4678. Min Range: -3.4678

Max Act: 3.0558. Min Act: -0.1700

Data Index: 281016 (C4 (Web Text))

Max Activating Token Index: 848

Text #18

Max Range: 3.4678. Min Range: -3.4678

Max Act: 3.0387. Min Act: -0.1700

Data Index: 1618797 (Python Code)

Max Activating Token Index: 133

Text #19

Max Range: 3.4678. Min Range: -3.4678

Max Act: 3.0281. Min Act: -0.1699

Data Index: 1582495 (Python Code)

Max Activating Token Index: 970