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

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

Neuron 675 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.3264. Min Range: -3.3264

Max Act: 3.3264. Min Act: -0.1700

Data Index: 1510420 (Python Code)

Max Activating Token Index: 431

Text #1

Max Range: 3.3264. Min Range: -3.3264

Max Act: 3.3107. Min Act: -0.1700

Data Index: 1578103 (Python Code)

Max Activating Token Index: 178

Text #2

Max Range: 3.3264. Min Range: -3.3264

Max Act: 3.2950. Min Act: -0.1700

Data Index: 1550354 (Python Code)

Max Activating Token Index: 319

Text #3

Max Range: 3.3264. Min Range: -3.3264

Max Act: 3.1850. Min Act: -0.1700

Data Index: 1620507 (Python Code)

Max Activating Token Index: 438

Text #4

Max Range: 3.3264. Min Range: -3.3264

Max Act: 3.2007. Min Act: -0.1700

Data Index: 1517702 (Python Code)

Max Activating Token Index: 602

Text #5

Max Range: 3.3264. Min Range: -3.3264

Max Act: 3.1850. Min Act: -0.1700

Data Index: 1445703 (Python Code)

Max Activating Token Index: 217

Text #6

Max Range: 3.3264. Min Range: -3.3264

Max Act: 3.2007. Min Act: -0.1700

Data Index: 1544351 (Python Code)

Max Activating Token Index: 495

Text #7

Max Range: 3.3264. Min Range: -3.3264

Max Act: 3.2007. Min Act: -0.1700

Data Index: 1592832 (Python Code)

Max Activating Token Index: 374

Text #8

Max Range: 3.3264. Min Range: -3.3264

Max Act: 3.1535. Min Act: -0.1700

Data Index: 1509883 (Python Code)

Max Activating Token Index: 665

Text #9

Max Range: 3.3264. Min Range: -3.3264

Max Act: 3.1220. Min Act: -0.1700

Data Index: 1597713 (Python Code)

Max Activating Token Index: 695

Text #10

Max Range: 3.3264. Min Range: -3.3264

Max Act: 3.1535. Min Act: -0.1700

Data Index: 1524866 (Python Code)

Max Activating Token Index: 70

Text #11

Max Range: 3.3264. Min Range: -3.3264

Max Act: 3.0905. Min Act: -0.1700

Data Index: 1442562 (Python Code)

Max Activating Token Index: 46

Text #12

Max Range: 3.3264. Min Range: -3.3264

Max Act: 3.1062. Min Act: -0.1700

Data Index: 1638888 (Python Code)

Max Activating Token Index: 506

Text #13

Max Range: 3.3264. Min Range: -3.3264

Max Act: 3.1062. Min Act: -0.1700

Data Index: 1472384 (Python Code)

Max Activating Token Index: 173

Text #14

Max Range: 3.3264. Min Range: -3.3264

Max Act: 3.1062. Min Act: -0.1700

Data Index: 1628996 (Python Code)

Max Activating Token Index: 729

Text #15

Max Range: 3.3264. Min Range: -3.3264

Max Act: 3.0747. Min Act: -0.1700

Data Index: 1399786 (Python Code)

Max Activating Token Index: 108

Text #16

Max Range: 3.3264. Min Range: -3.3264

Max Act: 3.0747. Min Act: -0.1700

Data Index: 1507665 (Python Code)

Max Activating Token Index: 173

Text #17

Max Range: 3.3264. Min Range: -3.3264

Max Act: 3.0747. Min Act: -0.1700

Data Index: 1526838 (Python Code)

Max Activating Token Index: 156

Text #18

Max Range: 3.3264. Min Range: -3.3264

Max Act: 3.0589. Min Act: -0.1700

Data Index: 1414488 (Python Code)

Max Activating Token Index: 134

Text #19

Max Range: 3.3264. Min Range: -3.3264

Max Act: 3.0115. Min Act: -0.1700

Data Index: 1528097 (Python Code)

Max Activating Token Index: 966