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

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

Neuron 608 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: 14.6720. Min Range: -14.6720

Max Act: 14.6720. Min Act: -0.1700

Data Index: 34057 (C4 (Web Text))

Max Activating Token Index: 28

Text #1

Max Range: 14.6720. Min Range: -14.6720

Max Act: 14.2345. Min Act: -0.1700

Data Index: 1483328 (Python Code)

Max Activating Token Index: 816

Text #2

Max Range: 14.6720. Min Range: -14.6720

Max Act: 14.1095. Min Act: -0.1700

Data Index: 1643779 (Python Code)

Max Activating Token Index: 673

Text #3

Max Range: 14.6720. Min Range: -14.6720

Max Act: 13.9845. Min Act: -0.1700

Data Index: 1423316 (Python Code)

Max Activating Token Index: 76

Text #4

Max Range: 14.6720. Min Range: -14.6720

Max Act: 13.3595. Min Act: -0.1699

Data Index: 1439139 (Python Code)

Max Activating Token Index: 989

Text #5

Max Range: 14.6720. Min Range: -14.6720

Max Act: 13.1720. Min Act: -0.1700

Data Index: 1641948 (Python Code)

Max Activating Token Index: 128

Text #6

Max Range: 14.6720. Min Range: -14.6720

Max Act: 12.9845. Min Act: -0.1700

Data Index: 935352 (C4 (Web Text))

Max Activating Token Index: 818

Text #7

Max Range: 14.6720. Min Range: -14.6720

Max Act: 12.7970. Min Act: -0.1700

Data Index: 483708 (C4 (Web Text))

Max Activating Token Index: 258

Text #8

Max Range: 14.6720. Min Range: -14.6720

Max Act: 12.2345. Min Act: -0.1700

Data Index: 1213837 (C4 (Web Text))

Max Activating Token Index: 989

Text #9

Max Range: 14.6720. Min Range: -14.6720

Max Act: 12.0470. Min Act: -0.1700

Data Index: 1380046 (Python Code)

Max Activating Token Index: 925

Text #10

Max Range: 14.6720. Min Range: -14.6720

Max Act: 12.0470. Min Act: -0.1700

Data Index: 955345 (C4 (Web Text))

Max Activating Token Index: 203

Text #11

Max Range: 14.6720. Min Range: -14.6720

Max Act: 11.9220. Min Act: -0.1700

Data Index: 1601263 (Python Code)

Max Activating Token Index: 39

Text #12

Max Range: 14.6720. Min Range: -14.6720

Max Act: 11.7970. Min Act: -0.1700

Data Index: 1449320 (Python Code)

Max Activating Token Index: 12

Text #13

Max Range: 14.6720. Min Range: -14.6720

Max Act: 11.5470. Min Act: -0.1700

Data Index: 1655744 (Python Code)

Max Activating Token Index: 326

Text #14

Max Range: 14.6720. Min Range: -14.6720

Max Act: 11.2345. Min Act: -0.1700

Data Index: 1173306 (C4 (Web Text))

Max Activating Token Index: 747

Text #15

Max Range: 14.6720. Min Range: -14.6720

Max Act: 11.0470. Min Act: -0.1700

Data Index: 1044588 (C4 (Web Text))

Max Activating Token Index: 125

Text #16

Max Range: 14.6720. Min Range: -14.6720

Max Act: 11.0470. Min Act: -0.1700

Data Index: 871104 (C4 (Web Text))

Max Activating Token Index: 679

Text #17

Max Range: 14.6720. Min Range: -14.6720

Max Act: 10.8595. Min Act: -0.1700

Data Index: 706918 (C4 (Web Text))

Max Activating Token Index: 609

Text #18

Max Range: 14.6720. Min Range: -14.6720

Max Act: 10.8595. Min Act: -0.1700

Data Index: 1649474 (Python Code)

Max Activating Token Index: 807

Text #19

Max Range: 14.6720. Min Range: -14.6720

Max Act: 10.9220. Min Act: -0.1700

Data Index: 1529790 (Python Code)

Max Activating Token Index: 710