Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 66 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 8.8834. Min Range: -8.8834

Max Act: 8.8834. Min Act: -0.1700

Data Index: 319376 (C4 (Web Text))

Max Activating Token Index: 20

Text #1

Max Range: 8.8834. Min Range: -8.8834

Max Act: 8.6334. Min Act: -0.1700

Data Index: 194258 (C4 (Web Text))

Max Activating Token Index: 7

Text #2

Max Range: 8.8834. Min Range: -8.8834

Max Act: 8.5709. Min Act: -0.1700

Data Index: 608372 (C4 (Web Text))

Max Activating Token Index: 516

Text #3

Max Range: 8.8834. Min Range: -8.8834

Max Act: 8.5084. Min Act: -0.1700

Data Index: 789211 (C4 (Web Text))

Max Activating Token Index: 66

Text #4

Max Range: 8.8834. Min Range: -8.8834

Max Act: 8.2584. Min Act: -0.1700

Data Index: 547119 (C4 (Web Text))

Max Activating Token Index: 613

Text #5

Max Range: 8.8834. Min Range: -8.8834

Max Act: 8.3834. Min Act: -0.1700

Data Index: 183529 (C4 (Web Text))

Max Activating Token Index: 899

Text #6

Max Range: 8.8834. Min Range: -8.8834

Max Act: 8.3834. Min Act: -0.1700

Data Index: 840721 (C4 (Web Text))

Max Activating Token Index: 1001

Text #7

Max Range: 8.8834. Min Range: -8.8834

Max Act: 8.2584. Min Act: -0.1700

Data Index: 47186 (C4 (Web Text))

Max Activating Token Index: 26

Text #8

Max Range: 8.8834. Min Range: -8.8834

Max Act: 8.1334. Min Act: -0.1700

Data Index: 501444 (C4 (Web Text))

Max Activating Token Index: 11

Text #9

Max Range: 8.8834. Min Range: -8.8834

Max Act: 8.0709. Min Act: -0.1700

Data Index: 253142 (C4 (Web Text))

Max Activating Token Index: 46

Text #10

Max Range: 8.8834. Min Range: -8.8834

Max Act: 8.0709. Min Act: -0.1700

Data Index: 349296 (C4 (Web Text))

Max Activating Token Index: 951

Text #11

Max Range: 8.8834. Min Range: -8.8834

Max Act: 8.1334. Min Act: -0.1699

Data Index: 349770 (C4 (Web Text))

Max Activating Token Index: 8

Text #12

Max Range: 8.8834. Min Range: -8.8834

Max Act: 8.0709. Min Act: -0.1700

Data Index: 505854 (C4 (Web Text))

Max Activating Token Index: 202

Text #13

Max Range: 8.8834. Min Range: -8.8834

Max Act: 8.0084. Min Act: -0.1700

Data Index: 339118 (C4 (Web Text))

Max Activating Token Index: 676

Text #14

Max Range: 8.8834. Min Range: -8.8834

Max Act: 8.0709. Min Act: -0.1700

Data Index: 290151 (C4 (Web Text))

Max Activating Token Index: 30

Text #15

Max Range: 8.8834. Min Range: -8.8834

Max Act: 8.0709. Min Act: -0.1700

Data Index: 223319 (C4 (Web Text))

Max Activating Token Index: 28

Text #16

Max Range: 8.8834. Min Range: -8.8834

Max Act: 7.9458. Min Act: -0.1700

Data Index: 195590 (C4 (Web Text))

Max Activating Token Index: 885

Text #17

Max Range: 8.8834. Min Range: -8.8834

Max Act: 8.3209. Min Act: -0.1700

Data Index: 395798 (C4 (Web Text))

Max Activating Token Index: 739

Text #18

Max Range: 8.8834. Min Range: -8.8834

Max Act: 8.0084. Min Act: -0.1700

Data Index: 334779 (C4 (Web Text))

Max Activating Token Index: 649

Text #19

Max Range: 8.8834. Min Range: -8.8834

Max Act: 8.0709. Min Act: -0.1700

Data Index: 498312 (C4 (Web Text))

Max Activating Token Index: 834