Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 284 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.3262. Min Range: -3.3262

Max Act: 3.3262. Min Act: -0.1700

Data Index: 915003 (C4 (Web Text))

Max Activating Token Index: 181

Text #1

Max Range: 3.3262. Min Range: -3.3262

Max Act: 3.2005. Min Act: -0.1700

Data Index: 1174970 (C4 (Web Text))

Max Activating Token Index: 154

Text #2

Max Range: 3.3262. Min Range: -3.3262

Max Act: 3.1690. Min Act: -0.1700

Data Index: 428436 (C4 (Web Text))

Max Activating Token Index: 850

Text #3

Max Range: 3.3262. Min Range: -3.3262

Max Act: 3.1375. Min Act: -0.1700

Data Index: 382132 (C4 (Web Text))

Max Activating Token Index: 396

Text #4

Max Range: 3.3262. Min Range: -3.3262

Max Act: 3.1375. Min Act: -0.1700

Data Index: 827231 (C4 (Web Text))

Max Activating Token Index: 192

Text #5

Max Range: 3.3262. Min Range: -3.3262

Max Act: 3.1218. Min Act: -0.1700

Data Index: 951809 (C4 (Web Text))

Max Activating Token Index: 400

Text #6

Max Range: 3.3262. Min Range: -3.3262

Max Act: 3.1218. Min Act: -0.1700

Data Index: 688750 (C4 (Web Text))

Max Activating Token Index: 711

Text #7

Max Range: 3.3262. Min Range: -3.3262

Max Act: 3.1060. Min Act: -0.1700

Data Index: 79084 (C4 (Web Text))

Max Activating Token Index: 15

Text #8

Max Range: 3.3262. Min Range: -3.3262

Max Act: 3.1060. Min Act: -0.1700

Data Index: 239535 (C4 (Web Text))

Max Activating Token Index: 162

Text #9

Max Range: 3.3262. Min Range: -3.3262

Max Act: 3.1060. Min Act: -0.1700

Data Index: 108345 (C4 (Web Text))

Max Activating Token Index: 240

Text #10

Max Range: 3.3262. Min Range: -3.3262

Max Act: 3.1060. Min Act: -0.1700

Data Index: 844860 (C4 (Web Text))

Max Activating Token Index: 420

Text #11

Max Range: 3.3262. Min Range: -3.3262

Max Act: 3.0902. Min Act: -0.1700

Data Index: 859775 (C4 (Web Text))

Max Activating Token Index: 577

Text #12

Max Range: 3.3262. Min Range: -3.3262

Max Act: 3.0902. Min Act: -0.1700

Data Index: 535656 (C4 (Web Text))

Max Activating Token Index: 855

Text #13

Max Range: 3.3262. Min Range: -3.3262

Max Act: 3.0587. Min Act: -0.1700

Data Index: 758209 (C4 (Web Text))

Max Activating Token Index: 13

Text #14

Max Range: 3.3262. Min Range: -3.3262

Max Act: 3.0745. Min Act: -0.1700

Data Index: 730669 (C4 (Web Text))

Max Activating Token Index: 740

Text #15

Max Range: 3.3262. Min Range: -3.3262

Max Act: 3.0745. Min Act: -0.1700

Data Index: 988748 (C4 (Web Text))

Max Activating Token Index: 798

Text #16

Max Range: 3.3262. Min Range: -3.3262

Max Act: 3.1060. Min Act: -0.1700

Data Index: 1151485 (C4 (Web Text))

Max Activating Token Index: 976

Text #17

Max Range: 3.3262. Min Range: -3.3262

Max Act: 3.0745. Min Act: -0.1700

Data Index: 517573 (C4 (Web Text))

Max Activating Token Index: 85

Text #18

Max Range: 3.3262. Min Range: -3.3262

Max Act: 3.0745. Min Act: -0.1700

Data Index: 27102 (C4 (Web Text))

Max Activating Token Index: 68

Text #19

Max Range: 3.3262. Min Range: -3.3262

Max Act: 3.0745. Min Act: -0.1700

Data Index: 325889 (C4 (Web Text))

Max Activating Token Index: 68