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

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

Neuron 450 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7293. Min Range: -3.7293

Max Act: 3.7293. Min Act: -0.1700

Data Index: 165009 (C4 (Web Text))

Max Activating Token Index: 811

Text #1

Max Range: 3.7293. Min Range: -3.7293

Max Act: 3.6667. Min Act: -0.1700

Data Index: 117650 (C4 (Web Text))

Max Activating Token Index: 665

Text #2

Max Range: 3.7293. Min Range: -3.7293

Max Act: 3.6667. Min Act: -0.1700

Data Index: 392072 (C4 (Web Text))

Max Activating Token Index: 675

Text #3

Max Range: 3.7293. Min Range: -3.7293

Max Act: 3.6354. Min Act: -0.1700

Data Index: 786792 (C4 (Web Text))

Max Activating Token Index: 823

Text #4

Max Range: 3.7293. Min Range: -3.7293

Max Act: 3.6041. Min Act: -0.1700

Data Index: 632603 (C4 (Web Text))

Max Activating Token Index: 845

Text #5

Max Range: 3.7293. Min Range: -3.7293

Max Act: 3.6041. Min Act: -0.1700

Data Index: 142713 (C4 (Web Text))

Max Activating Token Index: 728

Text #6

Max Range: 3.7293. Min Range: -3.7293

Max Act: 3.6354. Min Act: -0.1700

Data Index: 628487 (C4 (Web Text))

Max Activating Token Index: 734

Text #7

Max Range: 3.7293. Min Range: -3.7293

Max Act: 3.6354. Min Act: -0.1700

Data Index: 764306 (C4 (Web Text))

Max Activating Token Index: 490

Text #8

Max Range: 3.7293. Min Range: -3.7293

Max Act: 3.5102. Min Act: -0.1700

Data Index: 812512 (C4 (Web Text))

Max Activating Token Index: 661

Text #9

Max Range: 3.7293. Min Range: -3.7293

Max Act: 3.5728. Min Act: -0.1700

Data Index: 259215 (C4 (Web Text))

Max Activating Token Index: 799

Text #10

Max Range: 3.7293. Min Range: -3.7293

Max Act: 3.5728. Min Act: -0.1700

Data Index: 285008 (C4 (Web Text))

Max Activating Token Index: 757

Text #11

Max Range: 3.7293. Min Range: -3.7293

Max Act: 3.5728. Min Act: -0.1700

Data Index: 486996 (C4 (Web Text))

Max Activating Token Index: 548

Text #12

Max Range: 3.7293. Min Range: -3.7293

Max Act: 3.5415. Min Act: -0.1700

Data Index: 922816 (C4 (Web Text))

Max Activating Token Index: 530

Text #13

Max Range: 3.7293. Min Range: -3.7293

Max Act: 3.5728. Min Act: -0.1700

Data Index: 78950 (C4 (Web Text))

Max Activating Token Index: 721

Text #14

Max Range: 3.7293. Min Range: -3.7293

Max Act: 3.5415. Min Act: -0.1700

Data Index: 50521 (C4 (Web Text))

Max Activating Token Index: 781

Text #15

Max Range: 3.7293. Min Range: -3.7293

Max Act: 3.4788. Min Act: -0.1700

Data Index: 258959 (C4 (Web Text))

Max Activating Token Index: 550

Text #16

Max Range: 3.7293. Min Range: -3.7293

Max Act: 3.5102. Min Act: -0.1700

Data Index: 249875 (C4 (Web Text))

Max Activating Token Index: 699

Text #17

Max Range: 3.7293. Min Range: -3.7293

Max Act: 3.4788. Min Act: -0.1700

Data Index: 588703 (C4 (Web Text))

Max Activating Token Index: 649

Text #18

Max Range: 3.7293. Min Range: -3.7293

Max Act: 3.5415. Min Act: -0.1700

Data Index: 822446 (C4 (Web Text))

Max Activating Token Index: 720

Text #19

Max Range: 3.7293. Min Range: -3.7293

Max Act: 3.5415. Min Act: -0.1700

Data Index: 653543 (C4 (Web Text))

Max Activating Token Index: 17