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

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

Neuron 1460 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1620. Min Range: -3.1620

Max Act: 3.1620. Min Act: -0.1700

Data Index: 1409811 (Python Code)

Max Activating Token Index: 11

Text #1

Max Range: 3.1620. Min Range: -3.1620

Max Act: 3.1463. Min Act: -0.1700

Data Index: 1443933 (Python Code)

Max Activating Token Index: 10

Text #2

Max Range: 3.1620. Min Range: -3.1620

Max Act: 3.0990. Min Act: -0.1700

Data Index: 1586751 (Python Code)

Max Activating Token Index: 73

Text #3

Max Range: 3.1620. Min Range: -3.1620

Max Act: 3.0517. Min Act: -0.1700

Data Index: 1571530 (Python Code)

Max Activating Token Index: 11

Text #4

Max Range: 3.1620. Min Range: -3.1620

Max Act: 3.0201. Min Act: -0.1700

Data Index: 1401057 (Python Code)

Max Activating Token Index: 23

Text #5

Max Range: 3.1620. Min Range: -3.1620

Max Act: 3.0359. Min Act: -0.1700

Data Index: 1463387 (Python Code)

Max Activating Token Index: 295

Text #6

Max Range: 3.1620. Min Range: -3.1620

Max Act: 2.9885. Min Act: -0.1700

Data Index: 1559408 (Python Code)

Max Activating Token Index: 29

Text #7

Max Range: 3.1620. Min Range: -3.1620

Max Act: 2.9885. Min Act: -0.1700

Data Index: 1478359 (Python Code)

Max Activating Token Index: 349

Text #8

Max Range: 3.1620. Min Range: -3.1620

Max Act: 2.9568. Min Act: -0.1700

Data Index: 1570339 (Python Code)

Max Activating Token Index: 140

Text #9

Max Range: 3.1620. Min Range: -3.1620

Max Act: 2.9568. Min Act: -0.1700

Data Index: 1517364 (Python Code)

Max Activating Token Index: 16

Text #10

Max Range: 3.1620. Min Range: -3.1620

Max Act: 2.9568. Min Act: -0.1700

Data Index: 1619060 (Python Code)

Max Activating Token Index: 8

Text #11

Max Range: 3.1620. Min Range: -3.1620

Max Act: 2.9568. Min Act: -0.1700

Data Index: 1552222 (Python Code)

Max Activating Token Index: 32

Text #12

Max Range: 3.1620. Min Range: -3.1620

Max Act: 2.9568. Min Act: -0.1700

Data Index: 1546602 (Python Code)

Max Activating Token Index: 11

Text #13

Max Range: 3.1620. Min Range: -3.1620

Max Act: 2.9410. Min Act: -0.1700

Data Index: 1379026 (Python Code)

Max Activating Token Index: 22

Text #14

Max Range: 3.1620. Min Range: -3.1620

Max Act: 2.9410. Min Act: -0.1700

Data Index: 1579277 (Python Code)

Max Activating Token Index: 19

Text #15

Max Range: 3.1620. Min Range: -3.1620

Max Act: 2.9410. Min Act: -0.1700

Data Index: 1614762 (Python Code)

Max Activating Token Index: 464

Text #16

Max Range: 3.1620. Min Range: -3.1620

Max Act: 2.9410. Min Act: -0.1700

Data Index: 1603536 (Python Code)

Max Activating Token Index: 7

Text #17

Max Range: 3.1620. Min Range: -3.1620

Max Act: 2.9251. Min Act: -0.1700

Data Index: 1371798 (Python Code)

Max Activating Token Index: 406

Text #18

Max Range: 3.1620. Min Range: -3.1620

Max Act: 2.9410. Min Act: -0.1700

Data Index: 1509307 (Python Code)

Max Activating Token Index: 5

Text #19

Max Range: 3.1620. Min Range: -3.1620

Max Act: 2.9251. Min Act: -0.1700

Data Index: 1390811 (Python Code)

Max Activating Token Index: 34