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

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

Neuron 568 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: 3.3795. Min Range: -3.3795

Max Act: 3.3795. Min Act: -0.1700

Data Index: 1412811 (Python Code)

Max Activating Token Index: 5

Text #1

Max Range: 3.3795. Min Range: -3.3795

Max Act: 3.3010. Min Act: -0.1700

Data Index: 1547709 (Python Code)

Max Activating Token Index: 2

Text #2

Max Range: 3.3795. Min Range: -3.3795

Max Act: 3.2067. Min Act: -0.1700

Data Index: 1639757 (Python Code)

Max Activating Token Index: 5

Text #3

Max Range: 3.3795. Min Range: -3.3795

Max Act: 3.1910. Min Act: -0.1700

Data Index: 1504696 (Python Code)

Max Activating Token Index: 7

Text #4

Max Range: 3.3795. Min Range: -3.3795

Max Act: 3.1280. Min Act: -0.1700

Data Index: 363128 (C4 (Web Text))

Max Activating Token Index: 571

Text #5

Max Range: 3.3795. Min Range: -3.3795

Max Act: 3.1437. Min Act: -0.1700

Data Index: 1446612 (Python Code)

Max Activating Token Index: 112

Text #6

Max Range: 3.3795. Min Range: -3.3795

Max Act: 3.1122. Min Act: -0.1700

Data Index: 1368859 (Python Code)

Max Activating Token Index: 786

Text #7

Max Range: 3.3795. Min Range: -3.3795

Max Act: 3.1280. Min Act: -0.1700

Data Index: 158320 (C4 (Web Text))

Max Activating Token Index: 816

Text #8

Max Range: 3.3795. Min Range: -3.3795

Max Act: 3.0807. Min Act: -0.1700

Data Index: 380909 (C4 (Web Text))

Max Activating Token Index: 994

Text #9

Max Range: 3.3795. Min Range: -3.3795

Max Act: 3.1122. Min Act: -0.1700

Data Index: 1216928 (C4 (Web Text))

Max Activating Token Index: 928

Text #10

Max Range: 3.3795. Min Range: -3.3795

Max Act: 3.0965. Min Act: -0.1700

Data Index: 766342 (C4 (Web Text))

Max Activating Token Index: 157

Text #11

Max Range: 3.3795. Min Range: -3.3795

Max Act: 3.0807. Min Act: -0.1700

Data Index: 1603170 (Python Code)

Max Activating Token Index: 50

Text #12

Max Range: 3.3795. Min Range: -3.3795

Max Act: 3.0649. Min Act: -0.1700

Data Index: 360639 (C4 (Web Text))

Max Activating Token Index: 749

Text #13

Max Range: 3.3795. Min Range: -3.3795

Max Act: 3.0649. Min Act: -0.1700

Data Index: 539286 (C4 (Web Text))

Max Activating Token Index: 96

Text #14

Max Range: 3.3795. Min Range: -3.3795

Max Act: 3.0965. Min Act: -0.1700

Data Index: 345987 (C4 (Web Text))

Max Activating Token Index: 514

Text #15

Max Range: 3.3795. Min Range: -3.3795

Max Act: 3.0649. Min Act: -0.1700

Data Index: 976646 (C4 (Web Text))

Max Activating Token Index: 171

Text #16

Max Range: 3.3795. Min Range: -3.3795

Max Act: 3.0649. Min Act: -0.1700

Data Index: 165826 (C4 (Web Text))

Max Activating Token Index: 824

Text #17

Max Range: 3.3795. Min Range: -3.3795

Max Act: 3.0649. Min Act: -0.1700

Data Index: 639068 (C4 (Web Text))

Max Activating Token Index: 839

Text #18

Max Range: 3.3795. Min Range: -3.3795

Max Act: 3.0807. Min Act: -0.1700

Data Index: 514722 (C4 (Web Text))

Max Activating Token Index: 496

Text #19

Max Range: 3.3795. Min Range: -3.3795

Max Act: 3.0807. Min Act: -0.1700

Data Index: 934360 (C4 (Web Text))

Max Activating Token Index: 823