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

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

Neuron 174 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: 3.7546. Min Range: -3.7546

Max Act: 3.7546. Min Act: -0.1700

Data Index: 56263 (C4 (Web Text))

Max Activating Token Index: 92

Text #1

Max Range: 3.7546. Min Range: -3.7546

Max Act: 3.6920. Min Act: -0.1700

Data Index: 1314846 (C4 (Web Text))

Max Activating Token Index: 216

Text #2

Max Range: 3.7546. Min Range: -3.7546

Max Act: 3.6607. Min Act: -0.1700

Data Index: 774633 (C4 (Web Text))

Max Activating Token Index: 294

Text #3

Max Range: 3.7546. Min Range: -3.7546

Max Act: 3.6607. Min Act: -0.1700

Data Index: 595758 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 3.7546. Min Range: -3.7546

Max Act: 3.6607. Min Act: -0.1700

Data Index: 141483 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 3.7546. Min Range: -3.7546

Max Act: 3.6294. Min Act: -0.1700

Data Index: 1222907 (C4 (Web Text))

Max Activating Token Index: 434

Text #6

Max Range: 3.7546. Min Range: -3.7546

Max Act: 3.5981. Min Act: -0.1700

Data Index: 749369 (C4 (Web Text))

Max Activating Token Index: 670

Text #7

Max Range: 3.7546. Min Range: -3.7546

Max Act: 3.5354. Min Act: -0.1700

Data Index: 357788 (C4 (Web Text))

Max Activating Token Index: 404

Text #8

Max Range: 3.7546. Min Range: -3.7546

Max Act: 3.5198. Min Act: -0.1700

Data Index: 330159 (C4 (Web Text))

Max Activating Token Index: 676

Text #9

Max Range: 3.7546. Min Range: -3.7546

Max Act: 3.5041. Min Act: -0.1700

Data Index: 222815 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 3.7546. Min Range: -3.7546

Max Act: 3.5198. Min Act: -0.1700

Data Index: 506227 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 3.7546. Min Range: -3.7546

Max Act: 3.5041. Min Act: -0.1700

Data Index: 1190887 (C4 (Web Text))

Max Activating Token Index: 892

Text #12

Max Range: 3.7546. Min Range: -3.7546

Max Act: 3.5041. Min Act: -0.1700

Data Index: 1270545 (C4 (Web Text))

Max Activating Token Index: 594

Text #13

Max Range: 3.7546. Min Range: -3.7546

Max Act: 3.4727. Min Act: -0.1700

Data Index: 242419 (C4 (Web Text))

Max Activating Token Index: 907

Text #14

Max Range: 3.7546. Min Range: -3.7546

Max Act: 3.4571. Min Act: -0.1700

Data Index: 87005 (C4 (Web Text))

Max Activating Token Index: 649

Text #15

Max Range: 3.7546. Min Range: -3.7546

Max Act: 3.4571. Min Act: -0.1700

Data Index: 336851 (C4 (Web Text))

Max Activating Token Index: 205

Text #16

Max Range: 3.7546. Min Range: -3.7546

Max Act: 3.4414. Min Act: -0.1700

Data Index: 128206 (C4 (Web Text))

Max Activating Token Index: 636

Text #17

Max Range: 3.7546. Min Range: -3.7546

Max Act: 3.4571. Min Act: -0.1700

Data Index: 522305 (C4 (Web Text))

Max Activating Token Index: 340

Text #18

Max Range: 3.7546. Min Range: -3.7546

Max Act: 3.4257. Min Act: -0.1700

Data Index: 281324 (C4 (Web Text))

Max Activating Token Index: 379

Text #19

Max Range: 3.7546. Min Range: -3.7546

Max Act: 3.4257. Min Act: -0.1700

Data Index: 247143 (C4 (Web Text))

Max Activating Token Index: 885