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

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

Neuron 1582 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: 3.8267. Min Range: -3.8267

Max Act: 3.8203. Min Act: -0.1700

Data Index: 1493003 (Python Code)

Max Activating Token Index: 269

Text #1

Max Range: 3.8267. Min Range: -3.8267

Max Act: 3.8245. Min Act: -0.1700

Data Index: 1472901 (Python Code)

Max Activating Token Index: 34

Text #2

Max Range: 3.8267. Min Range: -3.8267

Max Act: 3.8267. Min Act: -0.1700

Data Index: 1568018 (Python Code)

Max Activating Token Index: 6

Text #3

Max Range: 3.8267. Min Range: -3.8267

Max Act: 3.7319. Min Act: -0.1700

Data Index: 1517063 (Python Code)

Max Activating Token Index: 18

Text #4

Max Range: 3.8267. Min Range: -3.8267

Max Act: 3.6845. Min Act: -0.1700

Data Index: 1365315 (Python Code)

Max Activating Token Index: 376

Text #5

Max Range: 3.8267. Min Range: -3.8267

Max Act: 3.6623. Min Act: -0.1700

Data Index: 1557808 (Python Code)

Max Activating Token Index: 766

Text #6

Max Range: 3.8267. Min Range: -3.8267

Max Act: 3.6770. Min Act: -0.1700

Data Index: 1365562 (Python Code)

Max Activating Token Index: 4

Text #7

Max Range: 3.8267. Min Range: -3.8267

Max Act: 3.6723. Min Act: -0.1700

Data Index: 1425087 (Python Code)

Max Activating Token Index: 349

Text #8

Max Range: 3.8267. Min Range: -3.8267

Max Act: 3.6813. Min Act: -0.1700

Data Index: 1645153 (Python Code)

Max Activating Token Index: 976

Text #9

Max Range: 3.8267. Min Range: -3.8267

Max Act: 3.6828. Min Act: -0.1700

Data Index: 1610663 (Python Code)

Max Activating Token Index: 805

Text #10

Max Range: 3.8267. Min Range: -3.8267

Max Act: 3.6691. Min Act: -0.1700

Data Index: 1413753 (Python Code)

Max Activating Token Index: 3

Text #11

Max Range: 3.8267. Min Range: -3.8267

Max Act: 3.6775. Min Act: -0.1700

Data Index: 1428584 (Python Code)

Max Activating Token Index: 13

Text #12

Max Range: 3.8267. Min Range: -3.8267

Max Act: 3.6713. Min Act: -0.1700

Data Index: 1409489 (Python Code)

Max Activating Token Index: 233

Text #13

Max Range: 3.8267. Min Range: -3.8267

Max Act: 3.6380. Min Act: -0.1700

Data Index: 1391162 (Python Code)

Max Activating Token Index: 41

Text #14

Max Range: 3.8267. Min Range: -3.8267

Max Act: 3.6402. Min Act: -0.1700

Data Index: 1514486 (Python Code)

Max Activating Token Index: 536

Text #15

Max Range: 3.8267. Min Range: -3.8267

Max Act: 3.6609. Min Act: -0.1700

Data Index: 140496 (C4 (Web Text))

Max Activating Token Index: 764

Text #16

Max Range: 3.8267. Min Range: -3.8267

Max Act: 3.6351. Min Act: -0.1700

Data Index: 1501807 (Python Code)

Max Activating Token Index: 60

Text #17

Max Range: 3.8267. Min Range: -3.8267

Max Act: 3.6328. Min Act: -0.1700

Data Index: 1647011 (Python Code)

Max Activating Token Index: 76

Text #18

Max Range: 3.8267. Min Range: -3.8267

Max Act: 3.6169. Min Act: -0.1700

Data Index: 1561622 (Python Code)

Max Activating Token Index: 91

Text #19

Max Range: 3.8267. Min Range: -3.8267

Max Act: 3.5907. Min Act: -0.1700

Data Index: 1500202 (Python Code)

Max Activating Token Index: 342