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

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

Neuron 666 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: 3.7734. Min Range: -3.7734

Max Act: 3.7734. Min Act: -0.1700

Data Index: 1154777 (C4 (Web Text))

Max Activating Token Index: 831

Text #1

Max Range: 3.7734. Min Range: -3.7734

Max Act: 3.7109. Min Act: -0.1700

Data Index: 938498 (C4 (Web Text))

Max Activating Token Index: 996

Text #2

Max Range: 3.7734. Min Range: -3.7734

Max Act: 3.7109. Min Act: -0.1700

Data Index: 943015 (C4 (Web Text))

Max Activating Token Index: 103

Text #3

Max Range: 3.7734. Min Range: -3.7734

Max Act: 3.6483. Min Act: -0.1700

Data Index: 243079 (C4 (Web Text))

Max Activating Token Index: 740

Text #4

Max Range: 3.7734. Min Range: -3.7734

Max Act: 3.6483. Min Act: -0.1700

Data Index: 23941 (C4 (Web Text))

Max Activating Token Index: 632

Text #5

Max Range: 3.7734. Min Range: -3.7734

Max Act: 3.5543. Min Act: -0.1700

Data Index: 816504 (C4 (Web Text))

Max Activating Token Index: 690

Text #6

Max Range: 3.7734. Min Range: -3.7734

Max Act: 3.6483. Min Act: -0.1700

Data Index: 595468 (C4 (Web Text))

Max Activating Token Index: 455

Text #7

Max Range: 3.7734. Min Range: -3.7734

Max Act: 3.6170. Min Act: -0.1700

Data Index: 1328327 (C4 (Web Text))

Max Activating Token Index: 256

Text #8

Max Range: 3.7734. Min Range: -3.7734

Max Act: 3.5856. Min Act: -0.1700

Data Index: 496814 (C4 (Web Text))

Max Activating Token Index: 123

Text #9

Max Range: 3.7734. Min Range: -3.7734

Max Act: 3.5700. Min Act: -0.1700

Data Index: 445638 (C4 (Web Text))

Max Activating Token Index: 571

Text #10

Max Range: 3.7734. Min Range: -3.7734

Max Act: 3.6013. Min Act: -0.1700

Data Index: 622848 (C4 (Web Text))

Max Activating Token Index: 796

Text #11

Max Range: 3.7734. Min Range: -3.7734

Max Act: 3.5856. Min Act: -0.1700

Data Index: 164383 (C4 (Web Text))

Max Activating Token Index: 698

Text #12

Max Range: 3.7734. Min Range: -3.7734

Max Act: 3.6013. Min Act: -0.1700

Data Index: 804757 (C4 (Web Text))

Max Activating Token Index: 376

Text #13

Max Range: 3.7734. Min Range: -3.7734

Max Act: 3.5230. Min Act: -0.1700

Data Index: 982529 (C4 (Web Text))

Max Activating Token Index: 787

Text #14

Max Range: 3.7734. Min Range: -3.7734

Max Act: 3.5543. Min Act: -0.1700

Data Index: 1124208 (C4 (Web Text))

Max Activating Token Index: 312

Text #15

Max Range: 3.7734. Min Range: -3.7734

Max Act: 3.5700. Min Act: -0.1700

Data Index: 112179 (C4 (Web Text))

Max Activating Token Index: 544

Text #16

Max Range: 3.7734. Min Range: -3.7734

Max Act: 3.5387. Min Act: -0.1700

Data Index: 2701 (C4 (Web Text))

Max Activating Token Index: 655

Text #17

Max Range: 3.7734. Min Range: -3.7734

Max Act: 3.5856. Min Act: -0.1700

Data Index: 1202710 (C4 (Web Text))

Max Activating Token Index: 605

Text #18

Max Range: 3.7734. Min Range: -3.7734

Max Act: 3.6013. Min Act: -0.1700

Data Index: 83464 (C4 (Web Text))

Max Activating Token Index: 434

Text #19

Max Range: 3.7734. Min Range: -3.7734

Max Act: 3.5387. Min Act: -0.1700

Data Index: 82152 (C4 (Web Text))

Max Activating Token Index: 838