Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 165 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.8349. Min Range: -3.8349

Max Act: 3.8349. Min Act: -0.1700

Data Index: 1372883 (Python Code)

Max Activating Token Index: 169

Text #1

Max Range: 3.8349. Min Range: -3.8349

Max Act: 3.7410. Min Act: -0.1700

Data Index: 1526156 (Python Code)

Max Activating Token Index: 951

Text #2

Max Range: 3.8349. Min Range: -3.8349

Max Act: 3.7254. Min Act: -0.1700

Data Index: 1454546 (Python Code)

Max Activating Token Index: 165

Text #3

Max Range: 3.8349. Min Range: -3.8349

Max Act: 3.7097. Min Act: -0.1700

Data Index: 1497827 (Python Code)

Max Activating Token Index: 618

Text #4

Max Range: 3.8349. Min Range: -3.8349

Max Act: 3.6784. Min Act: -0.1700

Data Index: 1538863 (Python Code)

Max Activating Token Index: 492

Text #5

Max Range: 3.8349. Min Range: -3.8349

Max Act: 3.6784. Min Act: -0.1700

Data Index: 1584971 (Python Code)

Max Activating Token Index: 116

Text #6

Max Range: 3.8349. Min Range: -3.8349

Max Act: 3.6471. Min Act: -0.1700

Data Index: 1448716 (Python Code)

Max Activating Token Index: 638

Text #7

Max Range: 3.8349. Min Range: -3.8349

Max Act: 3.6471. Min Act: -0.1700

Data Index: 1588527 (Python Code)

Max Activating Token Index: 660

Text #8

Max Range: 3.8349. Min Range: -3.8349

Max Act: 3.6315. Min Act: -0.1700

Data Index: 1652206 (Python Code)

Max Activating Token Index: 516

Text #9

Max Range: 3.8349. Min Range: -3.8349

Max Act: 3.6002. Min Act: -0.1700

Data Index: 896284 (C4 (Web Text))

Max Activating Token Index: 19

Text #10

Max Range: 3.8349. Min Range: -3.8349

Max Act: 3.6002. Min Act: -0.1700

Data Index: 62969 (C4 (Web Text))

Max Activating Token Index: 956

Text #11

Max Range: 3.8349. Min Range: -3.8349

Max Act: 3.6002. Min Act: -0.1700

Data Index: 1649894 (Python Code)

Max Activating Token Index: 282

Text #12

Max Range: 3.8349. Min Range: -3.8349

Max Act: 3.5845. Min Act: -0.1700

Data Index: 1379944 (Python Code)

Max Activating Token Index: 997

Text #13

Max Range: 3.8349. Min Range: -3.8349

Max Act: 3.5689. Min Act: -0.1700

Data Index: 1409896 (Python Code)

Max Activating Token Index: 636

Text #14

Max Range: 3.8349. Min Range: -3.8349

Max Act: 3.5689. Min Act: -0.1700

Data Index: 1645110 (Python Code)

Max Activating Token Index: 445

Text #15

Max Range: 3.8349. Min Range: -3.8349

Max Act: 3.5532. Min Act: -0.1700

Data Index: 1268742 (C4 (Web Text))

Max Activating Token Index: 619

Text #16

Max Range: 3.8349. Min Range: -3.8349

Max Act: 3.5532. Min Act: -0.1700

Data Index: 1480180 (Python Code)

Max Activating Token Index: 10

Text #17

Max Range: 3.8349. Min Range: -3.8349

Max Act: 3.5532. Min Act: -0.1700

Data Index: 1040254 (C4 (Web Text))

Max Activating Token Index: 693

Text #18

Max Range: 3.8349. Min Range: -3.8349

Max Act: 3.5219. Min Act: -0.1700

Data Index: 1515610 (Python Code)

Max Activating Token Index: 113

Text #19

Max Range: 3.8349. Min Range: -3.8349

Max Act: 3.5375. Min Act: -0.1700

Data Index: 1606474 (Python Code)

Max Activating Token Index: 644