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

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

Neuron 388 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: 5.7642. Min Range: -5.7642

Max Act: 5.7642. Min Act: -0.1700

Data Index: 622100 (C4 (Web Text))

Max Activating Token Index: 761

Text #1

Max Range: 5.7642. Min Range: -5.7642

Max Act: 5.7329. Min Act: -0.1700

Data Index: 919801 (C4 (Web Text))

Max Activating Token Index: 916

Text #2

Max Range: 5.7642. Min Range: -5.7642

Max Act: 5.6079. Min Act: -0.1700

Data Index: 1090059 (C4 (Web Text))

Max Activating Token Index: 90

Text #3

Max Range: 5.7642. Min Range: -5.7642

Max Act: 5.5142. Min Act: -0.1700

Data Index: 1340151 (C4 (Web Text))

Max Activating Token Index: 865

Text #4

Max Range: 5.7642. Min Range: -5.7642

Max Act: 5.5454. Min Act: -0.1700

Data Index: 349638 (C4 (Web Text))

Max Activating Token Index: 389

Text #5

Max Range: 5.7642. Min Range: -5.7642

Max Act: 5.5454. Min Act: -0.1700

Data Index: 1350258 (C4 (Web Text))

Max Activating Token Index: 270

Text #6

Max Range: 5.7642. Min Range: -5.7642

Max Act: 5.5767. Min Act: -0.1700

Data Index: 344109 (C4 (Web Text))

Max Activating Token Index: 404

Text #7

Max Range: 5.7642. Min Range: -5.7642

Max Act: 5.5767. Min Act: -0.1700

Data Index: 250619 (C4 (Web Text))

Max Activating Token Index: 276

Text #8

Max Range: 5.7642. Min Range: -5.7642

Max Act: 5.5142. Min Act: -0.1700

Data Index: 1250426 (C4 (Web Text))

Max Activating Token Index: 618

Text #9

Max Range: 5.7642. Min Range: -5.7642

Max Act: 5.5142. Min Act: -0.1700

Data Index: 877138 (C4 (Web Text))

Max Activating Token Index: 499

Text #10

Max Range: 5.7642. Min Range: -5.7642

Max Act: 5.5142. Min Act: -0.1700

Data Index: 47325 (C4 (Web Text))

Max Activating Token Index: 150

Text #11

Max Range: 5.7642. Min Range: -5.7642

Max Act: 5.4517. Min Act: -0.1700

Data Index: 931793 (C4 (Web Text))

Max Activating Token Index: 928

Text #12

Max Range: 5.7642. Min Range: -5.7642

Max Act: 5.4829. Min Act: -0.1700

Data Index: 1232375 (C4 (Web Text))

Max Activating Token Index: 723

Text #13

Max Range: 5.7642. Min Range: -5.7642

Max Act: 5.4829. Min Act: -0.1700

Data Index: 265789 (C4 (Web Text))

Max Activating Token Index: 117

Text #14

Max Range: 5.7642. Min Range: -5.7642

Max Act: 5.4204. Min Act: -0.1700

Data Index: 492384 (C4 (Web Text))

Max Activating Token Index: 701

Text #15

Max Range: 5.7642. Min Range: -5.7642

Max Act: 5.4204. Min Act: -0.1700

Data Index: 209423 (C4 (Web Text))

Max Activating Token Index: 235

Text #16

Max Range: 5.7642. Min Range: -5.7642

Max Act: 5.4517. Min Act: -0.1700

Data Index: 252756 (C4 (Web Text))

Max Activating Token Index: 900

Text #17

Max Range: 5.7642. Min Range: -5.7642

Max Act: 5.4829. Min Act: -0.1700

Data Index: 717007 (C4 (Web Text))

Max Activating Token Index: 977

Text #18

Max Range: 5.7642. Min Range: -5.7642

Max Act: 5.4829. Min Act: -0.1700

Data Index: 1096295 (C4 (Web Text))

Max Activating Token Index: 234

Text #19

Max Range: 5.7642. Min Range: -5.7642

Max Act: 5.4204. Min Act: -0.1700

Data Index: 354709 (C4 (Web Text))

Max Activating Token Index: 150