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

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

Neuron 11 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1375. Min Range: -3.1375

Max Act: 3.1375. Min Act: -0.1700

Data Index: 1472853 (Python Code)

Max Activating Token Index: 37

Text #1

Max Range: 3.1375. Min Range: -3.1375

Max Act: 3.1218. Min Act: -0.1700

Data Index: 1627817 (Python Code)

Max Activating Token Index: 30

Text #2

Max Range: 3.1375. Min Range: -3.1375

Max Act: 3.0429. Min Act: -0.1700

Data Index: 1506105 (Python Code)

Max Activating Token Index: 86

Text #3

Max Range: 3.1375. Min Range: -3.1375

Max Act: 3.0113. Min Act: -0.1700

Data Index: 1500385 (Python Code)

Max Activating Token Index: 35

Text #4

Max Range: 3.1375. Min Range: -3.1375

Max Act: 2.9955. Min Act: -0.1700

Data Index: 1647585 (Python Code)

Max Activating Token Index: 11

Text #5

Max Range: 3.1375. Min Range: -3.1375

Max Act: 2.9955. Min Act: -0.1700

Data Index: 1442362 (Python Code)

Max Activating Token Index: 12

Text #6

Max Range: 3.1375. Min Range: -3.1375

Max Act: 2.9797. Min Act: -0.1700

Data Index: 1445700 (Python Code)

Max Activating Token Index: 305

Text #7

Max Range: 3.1375. Min Range: -3.1375

Max Act: 2.9955. Min Act: -0.1700

Data Index: 1395493 (Python Code)

Max Activating Token Index: 18

Text #8

Max Range: 3.1375. Min Range: -3.1375

Max Act: 2.9955. Min Act: -0.1700

Data Index: 1415070 (Python Code)

Max Activating Token Index: 15

Text #9

Max Range: 3.1375. Min Range: -3.1375

Max Act: 2.9797. Min Act: -0.1700

Data Index: 1360025 (Python Code)

Max Activating Token Index: 61

Text #10

Max Range: 3.1375. Min Range: -3.1375

Max Act: 2.9955. Min Act: -0.1700

Data Index: 1420481 (Python Code)

Max Activating Token Index: 210

Text #11

Max Range: 3.1375. Min Range: -3.1375

Max Act: 2.9955. Min Act: -0.1700

Data Index: 1457926 (Python Code)

Max Activating Token Index: 31

Text #12

Max Range: 3.1375. Min Range: -3.1375

Max Act: 2.9955. Min Act: -0.1700

Data Index: 1380139 (Python Code)

Max Activating Token Index: 22

Text #13

Max Range: 3.1375. Min Range: -3.1375

Max Act: 2.9797. Min Act: -0.1700

Data Index: 1579304 (Python Code)

Max Activating Token Index: 22

Text #14

Max Range: 3.1375. Min Range: -3.1375

Max Act: 2.9797. Min Act: -0.1700

Data Index: 1477952 (Python Code)

Max Activating Token Index: 23

Text #15

Max Range: 3.1375. Min Range: -3.1375

Max Act: 2.9955. Min Act: -0.1700

Data Index: 1610543 (Python Code)

Max Activating Token Index: 13

Text #16

Max Range: 3.1375. Min Range: -3.1375

Max Act: 2.9797. Min Act: -0.1700

Data Index: 1484512 (Python Code)

Max Activating Token Index: 11

Text #17

Max Range: 3.1375. Min Range: -3.1375

Max Act: 2.9639. Min Act: -0.1700

Data Index: 1366086 (Python Code)

Max Activating Token Index: 11

Text #18

Max Range: 3.1375. Min Range: -3.1375

Max Act: 2.9955. Min Act: -0.1700

Data Index: 1620756 (Python Code)

Max Activating Token Index: 24

Text #19

Max Range: 3.1375. Min Range: -3.1375

Max Act: 2.9797. Min Act: -0.1700

Data Index: 1390570 (Python Code)

Max Activating Token Index: 34