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

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

Neuron 2033 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: 3.8903. Min Range: -3.8903

Max Act: 3.8903. Min Act: -0.1700

Data Index: 1638278 (Python Code)

Max Activating Token Index: 568

Text #1

Max Range: 3.8903. Min Range: -3.8903

Max Act: 3.8591. Min Act: -0.1700

Data Index: 1407864 (Python Code)

Max Activating Token Index: 669

Text #2

Max Range: 3.8903. Min Range: -3.8903

Max Act: 3.8278. Min Act: -0.1700

Data Index: 1403845 (Python Code)

Max Activating Token Index: 926

Text #3

Max Range: 3.8903. Min Range: -3.8903

Max Act: 3.8121. Min Act: -0.1700

Data Index: 1494529 (Python Code)

Max Activating Token Index: 176

Text #4

Max Range: 3.8903. Min Range: -3.8903

Max Act: 3.8434. Min Act: -0.1700

Data Index: 1504838 (Python Code)

Max Activating Token Index: 387

Text #5

Max Range: 3.8903. Min Range: -3.8903

Max Act: 3.7809. Min Act: -0.1700

Data Index: 1612714 (Python Code)

Max Activating Token Index: 430

Text #6

Max Range: 3.8903. Min Range: -3.8903

Max Act: 3.7809. Min Act: -0.1700

Data Index: 1436425 (Python Code)

Max Activating Token Index: 619

Text #7

Max Range: 3.8903. Min Range: -3.8903

Max Act: 3.8121. Min Act: -0.1700

Data Index: 1537030 (Python Code)

Max Activating Token Index: 737

Text #8

Max Range: 3.8903. Min Range: -3.8903

Max Act: 3.8121. Min Act: -0.1700

Data Index: 1462330 (Python Code)

Max Activating Token Index: 763

Text #9

Max Range: 3.8903. Min Range: -3.8903

Max Act: 3.8121. Min Act: -0.1700

Data Index: 1360557 (Python Code)

Max Activating Token Index: 809

Text #10

Max Range: 3.8903. Min Range: -3.8903

Max Act: 3.8121. Min Act: -0.1700

Data Index: 1628121 (Python Code)

Max Activating Token Index: 908

Text #11

Max Range: 3.8903. Min Range: -3.8903

Max Act: 3.7965. Min Act: -0.1700

Data Index: 1453910 (Python Code)

Max Activating Token Index: 964

Text #12

Max Range: 3.8903. Min Range: -3.8903

Max Act: 3.7809. Min Act: -0.1700

Data Index: 1393009 (Python Code)

Max Activating Token Index: 55

Text #13

Max Range: 3.8903. Min Range: -3.8903

Max Act: 3.7652. Min Act: -0.1700

Data Index: 1395792 (Python Code)

Max Activating Token Index: 91

Text #14

Max Range: 3.8903. Min Range: -3.8903

Max Act: 3.7652. Min Act: -0.1700

Data Index: 1593453 (Python Code)

Max Activating Token Index: 708

Text #15

Max Range: 3.8903. Min Range: -3.8903

Max Act: 3.7965. Min Act: -0.1700

Data Index: 1561285 (Python Code)

Max Activating Token Index: 152

Text #16

Max Range: 3.8903. Min Range: -3.8903

Max Act: 3.7965. Min Act: -0.1700

Data Index: 1618394 (Python Code)

Max Activating Token Index: 160

Text #17

Max Range: 3.8903. Min Range: -3.8903

Max Act: 3.7339. Min Act: -0.1700

Data Index: 1473970 (Python Code)

Max Activating Token Index: 375

Text #18

Max Range: 3.8903. Min Range: -3.8903

Max Act: 3.7339. Min Act: -0.1700

Data Index: 1574861 (Python Code)

Max Activating Token Index: 799

Text #19

Max Range: 3.8903. Min Range: -3.8903

Max Act: 3.7652. Min Act: -0.1700

Data Index: 1486398 (Python Code)

Max Activating Token Index: 474