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

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

Neuron 1854 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9174. Min Range: -3.9174

Max Act: 3.9174. Min Act: -0.1700

Data Index: 1477856 (Python Code)

Max Activating Token Index: 271

Text #1

Max Range: 3.9174. Min Range: -3.9174

Max Act: 3.8236. Min Act: -0.1700

Data Index: 1494390 (Python Code)

Max Activating Token Index: 1012

Text #2

Max Range: 3.9174. Min Range: -3.9174

Max Act: 3.7923. Min Act: -0.1700

Data Index: 1494094 (Python Code)

Max Activating Token Index: 650

Text #3

Max Range: 3.9174. Min Range: -3.9174

Max Act: 3.7610. Min Act: -0.1700

Data Index: 1553176 (Python Code)

Max Activating Token Index: 565

Text #4

Max Range: 3.9174. Min Range: -3.9174

Max Act: 3.7610. Min Act: -0.1700

Data Index: 1517531 (Python Code)

Max Activating Token Index: 571

Text #5

Max Range: 3.9174. Min Range: -3.9174

Max Act: 3.6358. Min Act: -0.1700

Data Index: 1443435 (Python Code)

Max Activating Token Index: 226

Text #6

Max Range: 3.9174. Min Range: -3.9174

Max Act: 3.6672. Min Act: -0.1700

Data Index: 1458211 (Python Code)

Max Activating Token Index: 519

Text #7

Max Range: 3.9174. Min Range: -3.9174

Max Act: 3.6672. Min Act: -0.1700

Data Index: 1596606 (Python Code)

Max Activating Token Index: 14

Text #8

Max Range: 3.9174. Min Range: -3.9174

Max Act: 3.6672. Min Act: -0.1700

Data Index: 1445615 (Python Code)

Max Activating Token Index: 196

Text #9

Max Range: 3.9174. Min Range: -3.9174

Max Act: 3.6672. Min Act: -0.1700

Data Index: 1541580 (Python Code)

Max Activating Token Index: 204

Text #10

Max Range: 3.9174. Min Range: -3.9174

Max Act: 3.6358. Min Act: -0.1700

Data Index: 1469558 (Python Code)

Max Activating Token Index: 5

Text #11

Max Range: 3.9174. Min Range: -3.9174

Max Act: 3.6358. Min Act: -0.1700

Data Index: 1574715 (Python Code)

Max Activating Token Index: 2

Text #12

Max Range: 3.9174. Min Range: -3.9174

Max Act: 3.5732. Min Act: -0.1700

Data Index: 1500308 (Python Code)

Max Activating Token Index: 6

Text #13

Max Range: 3.9174. Min Range: -3.9174

Max Act: 3.5419. Min Act: -0.1700

Data Index: 1384469 (Python Code)

Max Activating Token Index: 3

Text #14

Max Range: 3.9174. Min Range: -3.9174

Max Act: 3.5732. Min Act: -0.1700

Data Index: 1440294 (Python Code)

Max Activating Token Index: 56

Text #15

Max Range: 3.9174. Min Range: -3.9174

Max Act: 3.5732. Min Act: -0.1700

Data Index: 1586796 (Python Code)

Max Activating Token Index: 4

Text #16

Max Range: 3.9174. Min Range: -3.9174

Max Act: 3.5419. Min Act: -0.1700

Data Index: 1474714 (Python Code)

Max Activating Token Index: 3

Text #17

Max Range: 3.9174. Min Range: -3.9174

Max Act: 3.5732. Min Act: -0.1700

Data Index: 1634295 (Python Code)

Max Activating Token Index: 152

Text #18

Max Range: 3.9174. Min Range: -3.9174

Max Act: 3.5732. Min Act: -0.1700

Data Index: 1529737 (Python Code)

Max Activating Token Index: 1020

Text #19

Max Range: 3.9174. Min Range: -3.9174

Max Act: 3.5419. Min Act: -0.1700

Data Index: 1421254 (Python Code)

Max Activating Token Index: 3