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

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

Neuron 607 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7737. Min Range: -3.7737

Max Act: 3.7737. Min Act: -0.1700

Data Index: 949959 (C4 (Web Text))

Max Activating Token Index: 28

Text #1

Max Range: 3.7737. Min Range: -3.7737

Max Act: 3.5859. Min Act: -0.1700

Data Index: 542762 (C4 (Web Text))

Max Activating Token Index: 410

Text #2

Max Range: 3.7737. Min Range: -3.7737

Max Act: 3.5233. Min Act: -0.1700

Data Index: 781513 (C4 (Web Text))

Max Activating Token Index: 835

Text #3

Max Range: 3.7737. Min Range: -3.7737

Max Act: 3.5233. Min Act: -0.1700

Data Index: 905267 (C4 (Web Text))

Max Activating Token Index: 349

Text #4

Max Range: 3.7737. Min Range: -3.7737

Max Act: 3.5233. Min Act: -0.1700

Data Index: 343789 (C4 (Web Text))

Max Activating Token Index: 471

Text #5

Max Range: 3.7737. Min Range: -3.7737

Max Act: 3.4919. Min Act: -0.1700

Data Index: 988274 (C4 (Web Text))

Max Activating Token Index: 526

Text #6

Max Range: 3.7737. Min Range: -3.7737

Max Act: 3.5233. Min Act: -0.1700

Data Index: 622136 (C4 (Web Text))

Max Activating Token Index: 187

Text #7

Max Range: 3.7737. Min Range: -3.7737

Max Act: 3.4919. Min Act: -0.1700

Data Index: 596623 (C4 (Web Text))

Max Activating Token Index: 854

Text #8

Max Range: 3.7737. Min Range: -3.7737

Max Act: 3.4919. Min Act: -0.1700

Data Index: 1188657 (C4 (Web Text))

Max Activating Token Index: 171

Text #9

Max Range: 3.7737. Min Range: -3.7737

Max Act: 3.4919. Min Act: -0.1700

Data Index: 986428 (C4 (Web Text))

Max Activating Token Index: 73

Text #10

Max Range: 3.7737. Min Range: -3.7737

Max Act: 3.4606. Min Act: -0.1700

Data Index: 760522 (C4 (Web Text))

Max Activating Token Index: 264

Text #11

Max Range: 3.7737. Min Range: -3.7737

Max Act: 3.4606. Min Act: -0.1700

Data Index: 472785 (C4 (Web Text))

Max Activating Token Index: 674

Text #12

Max Range: 3.7737. Min Range: -3.7737

Max Act: 3.4292. Min Act: -0.1700

Data Index: 73231 (C4 (Web Text))

Max Activating Token Index: 358

Text #13

Max Range: 3.7737. Min Range: -3.7737

Max Act: 3.4606. Min Act: -0.1700

Data Index: 201029 (C4 (Web Text))

Max Activating Token Index: 1021

Text #14

Max Range: 3.7737. Min Range: -3.7737

Max Act: 3.4606. Min Act: -0.1700

Data Index: 111256 (C4 (Web Text))

Max Activating Token Index: 12

Text #15

Max Range: 3.7737. Min Range: -3.7737

Max Act: 3.4292. Min Act: -0.1700

Data Index: 1620419 (Python Code)

Max Activating Token Index: 927

Text #16

Max Range: 3.7737. Min Range: -3.7737

Max Act: 3.4292. Min Act: -0.1700

Data Index: 1290522 (C4 (Web Text))

Max Activating Token Index: 218

Text #17

Max Range: 3.7737. Min Range: -3.7737

Max Act: 3.4292. Min Act: -0.1700

Data Index: 548723 (C4 (Web Text))

Max Activating Token Index: 789

Text #18

Max Range: 3.7737. Min Range: -3.7737

Max Act: 3.4292. Min Act: -0.1700

Data Index: 1211752 (C4 (Web Text))

Max Activating Token Index: 41

Text #19

Max Range: 3.7737. Min Range: -3.7737

Max Act: 3.4292. Min Act: -0.1700

Data Index: 467193 (C4 (Web Text))

Max Activating Token Index: 89