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

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

Neuron 855 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: 3.4350. Min Range: -3.4350

Max Act: 3.4350. Min Act: -0.1700

Data Index: 1367229 (Python Code)

Max Activating Token Index: 149

Text #1

Max Range: 3.4350. Min Range: -3.4350

Max Act: 3.3723. Min Act: -0.1700

Data Index: 1513303 (Python Code)

Max Activating Token Index: 77

Text #2

Max Range: 3.4350. Min Range: -3.4350

Max Act: 3.3879. Min Act: -0.1700

Data Index: 1411161 (Python Code)

Max Activating Token Index: 803

Text #3

Max Range: 3.4350. Min Range: -3.4350

Max Act: 3.3409. Min Act: -0.1700

Data Index: 1630222 (Python Code)

Max Activating Token Index: 4

Text #4

Max Range: 3.4350. Min Range: -3.4350

Max Act: 3.3566. Min Act: -0.1700

Data Index: 1448216 (Python Code)

Max Activating Token Index: 583

Text #5

Max Range: 3.4350. Min Range: -3.4350

Max Act: 3.3252. Min Act: -0.1700

Data Index: 1622543 (Python Code)

Max Activating Token Index: 328

Text #6

Max Range: 3.4350. Min Range: -3.4350

Max Act: 3.3095. Min Act: -0.1700

Data Index: 1486777 (Python Code)

Max Activating Token Index: 26

Text #7

Max Range: 3.4350. Min Range: -3.4350

Max Act: 3.3409. Min Act: -0.1700

Data Index: 1592994 (Python Code)

Max Activating Token Index: 77

Text #8

Max Range: 3.4350. Min Range: -3.4350

Max Act: 3.2938. Min Act: -0.1700

Data Index: 1515827 (Python Code)

Max Activating Token Index: 36

Text #9

Max Range: 3.4350. Min Range: -3.4350

Max Act: 3.2781. Min Act: -0.1700

Data Index: 1547701 (Python Code)

Max Activating Token Index: 346

Text #10

Max Range: 3.4350. Min Range: -3.4350

Max Act: 3.2781. Min Act: -0.1700

Data Index: 1489188 (Python Code)

Max Activating Token Index: 531

Text #11

Max Range: 3.4350. Min Range: -3.4350

Max Act: 3.2938. Min Act: -0.1700

Data Index: 1543764 (Python Code)

Max Activating Token Index: 227

Text #12

Max Range: 3.4350. Min Range: -3.4350

Max Act: 3.2938. Min Act: -0.1700

Data Index: 1469468 (Python Code)

Max Activating Token Index: 5

Text #13

Max Range: 3.4350. Min Range: -3.4350

Max Act: 3.2781. Min Act: -0.1700

Data Index: 1360783 (Python Code)

Max Activating Token Index: 9

Text #14

Max Range: 3.4350. Min Range: -3.4350

Max Act: 3.2781. Min Act: -0.1700

Data Index: 1598256 (Python Code)

Max Activating Token Index: 627

Text #15

Max Range: 3.4350. Min Range: -3.4350

Max Act: 3.3095. Min Act: -0.1700

Data Index: 1585039 (Python Code)

Max Activating Token Index: 179

Text #16

Max Range: 3.4350. Min Range: -3.4350

Max Act: 3.2309. Min Act: -0.1700

Data Index: 1555117 (Python Code)

Max Activating Token Index: 106

Text #17

Max Range: 3.4350. Min Range: -3.4350

Max Act: 3.2623. Min Act: -0.1700

Data Index: 1613023 (Python Code)

Max Activating Token Index: 297

Text #18

Max Range: 3.4350. Min Range: -3.4350

Max Act: 3.2466. Min Act: -0.1700

Data Index: 1412033 (Python Code)

Max Activating Token Index: 16

Text #19

Max Range: 3.4350. Min Range: -3.4350

Max Act: 3.2466. Min Act: -0.1700

Data Index: 1525250 (Python Code)

Max Activating Token Index: 89