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

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

Neuron 532 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.6185. Min Range: -5.6185

Max Act: 5.6185. Min Act: -0.1700

Data Index: 1044532 (C4 (Web Text))

Max Activating Token Index: 31

Text #1

Max Range: 5.6185. Min Range: -5.6185

Max Act: 5.4935. Min Act: -0.1700

Data Index: 241438 (C4 (Web Text))

Max Activating Token Index: 415

Text #2

Max Range: 5.6185. Min Range: -5.6185

Max Act: 5.3685. Min Act: -0.1700

Data Index: 618403 (C4 (Web Text))

Max Activating Token Index: 933

Text #3

Max Range: 5.6185. Min Range: -5.6185

Max Act: 5.3685. Min Act: -0.1700

Data Index: 1013076 (C4 (Web Text))

Max Activating Token Index: 735

Text #4

Max Range: 5.6185. Min Range: -5.6185

Max Act: 5.3997. Min Act: -0.1700

Data Index: 665005 (C4 (Web Text))

Max Activating Token Index: 181

Text #5

Max Range: 5.6185. Min Range: -5.6185

Max Act: 5.3685. Min Act: -0.1699

Data Index: 326680 (C4 (Web Text))

Max Activating Token Index: 198

Text #6

Max Range: 5.6185. Min Range: -5.6185

Max Act: 5.3685. Min Act: -0.1700

Data Index: 467642 (C4 (Web Text))

Max Activating Token Index: 264

Text #7

Max Range: 5.6185. Min Range: -5.6185

Max Act: 5.3060. Min Act: -0.1673

Data Index: 612227 (C4 (Web Text))

Max Activating Token Index: 777

Text #8

Max Range: 5.6185. Min Range: -5.6185

Max Act: 5.3372. Min Act: -0.1700

Data Index: 543678 (C4 (Web Text))

Max Activating Token Index: 144

Text #9

Max Range: 5.6185. Min Range: -5.6185

Max Act: 5.2747. Min Act: -0.1700

Data Index: 613371 (C4 (Web Text))

Max Activating Token Index: 294

Text #10

Max Range: 5.6185. Min Range: -5.6185

Max Act: 5.1810. Min Act: -0.1700

Data Index: 718214 (C4 (Web Text))

Max Activating Token Index: 862

Text #11

Max Range: 5.6185. Min Range: -5.6185

Max Act: 5.2435. Min Act: -0.1700

Data Index: 973133 (C4 (Web Text))

Max Activating Token Index: 7

Text #12

Max Range: 5.6185. Min Range: -5.6185

Max Act: 5.2435. Min Act: -0.1700

Data Index: 448081 (C4 (Web Text))

Max Activating Token Index: 7

Text #13

Max Range: 5.6185. Min Range: -5.6185

Max Act: 5.2747. Min Act: -0.1700

Data Index: 172852 (C4 (Web Text))

Max Activating Token Index: 15

Text #14

Max Range: 5.6185. Min Range: -5.6185

Max Act: 5.2435. Min Act: -0.1700

Data Index: 493472 (C4 (Web Text))

Max Activating Token Index: 295

Text #15

Max Range: 5.6185. Min Range: -5.6185

Max Act: 5.2122. Min Act: -0.1700

Data Index: 881800 (C4 (Web Text))

Max Activating Token Index: 554

Text #16

Max Range: 5.6185. Min Range: -5.6185

Max Act: 5.1497. Min Act: -0.1700

Data Index: 246481 (C4 (Web Text))

Max Activating Token Index: 405

Text #17

Max Range: 5.6185. Min Range: -5.6185

Max Act: 5.2122. Min Act: -0.1700

Data Index: 471629 (C4 (Web Text))

Max Activating Token Index: 585

Text #18

Max Range: 5.6185. Min Range: -5.6185

Max Act: 5.1497. Min Act: -0.1700

Data Index: 992159 (C4 (Web Text))

Max Activating Token Index: 18

Text #19

Max Range: 5.6185. Min Range: -5.6185

Max Act: 5.2122. Min Act: -0.1700

Data Index: 730696 (C4 (Web Text))

Max Activating Token Index: 249