Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1450 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.6314. Min Range: -3.6314

Max Act: 3.6314. Min Act: -0.1700

Data Index: 1420727 (Python Code)

Max Activating Token Index: 28

Text #1

Max Range: 3.6314. Min Range: -3.6314

Max Act: 3.6314. Min Act: -0.1700

Data Index: 1381697 (Python Code)

Max Activating Token Index: 302

Text #2

Max Range: 3.6314. Min Range: -3.6314

Max Act: 3.6001. Min Act: -0.1700

Data Index: 1482113 (Python Code)

Max Activating Token Index: 520

Text #3

Max Range: 3.6314. Min Range: -3.6314

Max Act: 3.6001. Min Act: -0.1700

Data Index: 1613214 (Python Code)

Max Activating Token Index: 506

Text #4

Max Range: 3.6314. Min Range: -3.6314

Max Act: 3.5688. Min Act: -0.1700

Data Index: 1428238 (Python Code)

Max Activating Token Index: 742

Text #5

Max Range: 3.6314. Min Range: -3.6314

Max Act: 3.6001. Min Act: -0.1700

Data Index: 1470380 (Python Code)

Max Activating Token Index: 22

Text #6

Max Range: 3.6314. Min Range: -3.6314

Max Act: 3.4748. Min Act: -0.1700

Data Index: 1568148 (Python Code)

Max Activating Token Index: 803

Text #7

Max Range: 3.6314. Min Range: -3.6314

Max Act: 3.5531. Min Act: -0.1700

Data Index: 1548169 (Python Code)

Max Activating Token Index: 263

Text #8

Max Range: 3.6314. Min Range: -3.6314

Max Act: 3.5374. Min Act: -0.1700

Data Index: 1470338 (Python Code)

Max Activating Token Index: 218

Text #9

Max Range: 3.6314. Min Range: -3.6314

Max Act: 3.5531. Min Act: -0.1700

Data Index: 1423757 (Python Code)

Max Activating Token Index: 700

Text #10

Max Range: 3.6314. Min Range: -3.6314

Max Act: 3.5218. Min Act: -0.1700

Data Index: 1630556 (Python Code)

Max Activating Token Index: 285

Text #11

Max Range: 3.6314. Min Range: -3.6314

Max Act: 3.4904. Min Act: -0.1700

Data Index: 1452803 (Python Code)

Max Activating Token Index: 41

Text #12

Max Range: 3.6314. Min Range: -3.6314

Max Act: 3.4904. Min Act: -0.1700

Data Index: 1454110 (Python Code)

Max Activating Token Index: 31

Text #13

Max Range: 3.6314. Min Range: -3.6314

Max Act: 3.5061. Min Act: -0.1700

Data Index: 1533107 (Python Code)

Max Activating Token Index: 380

Text #14

Max Range: 3.6314. Min Range: -3.6314

Max Act: 3.4904. Min Act: -0.1700

Data Index: 1596392 (Python Code)

Max Activating Token Index: 280

Text #15

Max Range: 3.6314. Min Range: -3.6314

Max Act: 3.4904. Min Act: -0.1700

Data Index: 1515711 (Python Code)

Max Activating Token Index: 276

Text #16

Max Range: 3.6314. Min Range: -3.6314

Max Act: 3.4904. Min Act: -0.1700

Data Index: 1503049 (Python Code)

Max Activating Token Index: 167

Text #17

Max Range: 3.6314. Min Range: -3.6314

Max Act: 3.4748. Min Act: -0.1700

Data Index: 1569715 (Python Code)

Max Activating Token Index: 59

Text #18

Max Range: 3.6314. Min Range: -3.6314

Max Act: 3.4748. Min Act: -0.1700

Data Index: 1540336 (Python Code)

Max Activating Token Index: 389

Text #19

Max Range: 3.6314. Min Range: -3.6314

Max Act: 3.4434. Min Act: -0.1700

Data Index: 1604260 (Python Code)

Max Activating Token Index: 859