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

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

Neuron 352 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: 5.8799. Min Range: -5.8799

Max Act: 5.8799. Min Act: -0.1700

Data Index: 77933 (C4 (Web Text))

Max Activating Token Index: 1014

Text #1

Max Range: 5.8799. Min Range: -5.8799

Max Act: 5.6611. Min Act: -0.1700

Data Index: 1453884 (Python Code)

Max Activating Token Index: 889

Text #2

Max Range: 5.8799. Min Range: -5.8799

Max Act: 5.6611. Min Act: -0.1700

Data Index: 1409131 (Python Code)

Max Activating Token Index: 901

Text #3

Max Range: 5.8799. Min Range: -5.8799

Max Act: 5.6924. Min Act: -0.1700

Data Index: 1441340 (Python Code)

Max Activating Token Index: 445

Text #4

Max Range: 5.8799. Min Range: -5.8799

Max Act: 5.6924. Min Act: -0.1700

Data Index: 1613842 (Python Code)

Max Activating Token Index: 645

Text #5

Max Range: 5.8799. Min Range: -5.8799

Max Act: 5.5986. Min Act: -0.1700

Data Index: 1032355 (C4 (Web Text))

Max Activating Token Index: 907

Text #6

Max Range: 5.8799. Min Range: -5.8799

Max Act: 5.5674. Min Act: -0.1700

Data Index: 1485906 (Python Code)

Max Activating Token Index: 239

Text #7

Max Range: 5.8799. Min Range: -5.8799

Max Act: 5.5361. Min Act: -0.1700

Data Index: 1534539 (Python Code)

Max Activating Token Index: 431

Text #8

Max Range: 5.8799. Min Range: -5.8799

Max Act: 5.5986. Min Act: -0.1700

Data Index: 1455908 (Python Code)

Max Activating Token Index: 187

Text #9

Max Range: 5.8799. Min Range: -5.8799

Max Act: 5.4736. Min Act: -0.1700

Data Index: 1382163 (Python Code)

Max Activating Token Index: 540

Text #10

Max Range: 5.8799. Min Range: -5.8799

Max Act: 5.4736. Min Act: -0.1700

Data Index: 1494288 (Python Code)

Max Activating Token Index: 373

Text #11

Max Range: 5.8799. Min Range: -5.8799

Max Act: 5.4736. Min Act: -0.1700

Data Index: 1374965 (Python Code)

Max Activating Token Index: 281

Text #12

Max Range: 5.8799. Min Range: -5.8799

Max Act: 5.4736. Min Act: -0.1700

Data Index: 1635740 (Python Code)

Max Activating Token Index: 634

Text #13

Max Range: 5.8799. Min Range: -5.8799

Max Act: 5.5361. Min Act: -0.1700

Data Index: 1477600 (Python Code)

Max Activating Token Index: 752

Text #14

Max Range: 5.8799. Min Range: -5.8799

Max Act: 5.5049. Min Act: -0.1700

Data Index: 1367379 (Python Code)

Max Activating Token Index: 345

Text #15

Max Range: 5.8799. Min Range: -5.8799

Max Act: 5.4736. Min Act: -0.1700

Data Index: 1434688 (Python Code)

Max Activating Token Index: 425

Text #16

Max Range: 5.8799. Min Range: -5.8799

Max Act: 5.4736. Min Act: -0.1700

Data Index: 1550011 (Python Code)

Max Activating Token Index: 284

Text #17

Max Range: 5.8799. Min Range: -5.8799

Max Act: 5.3799. Min Act: -0.1700

Data Index: 1537884 (Python Code)

Max Activating Token Index: 229

Text #18

Max Range: 5.8799. Min Range: -5.8799

Max Act: 5.4111. Min Act: -0.1700

Data Index: 1528134 (Python Code)

Max Activating Token Index: 700

Text #19

Max Range: 5.8799. Min Range: -5.8799

Max Act: 5.4424. Min Act: -0.1700

Data Index: 1478224 (Python Code)

Max Activating Token Index: 450