Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 1552 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 4.0807. Min Range: -4.0807

Max Act: 4.0807. Min Act: -0.1700

Data Index: 114118 (C4 (Web Text))

Max Activating Token Index: 925

Text #1

Max Range: 4.0807. Min Range: -4.0807

Max Act: 4.0083. Min Act: -0.1700

Data Index: 50889 (C4 (Web Text))

Max Activating Token Index: 519

Text #2

Max Range: 4.0807. Min Range: -4.0807

Max Act: 3.9844. Min Act: -0.1697

Data Index: 168467 (C4 (Web Text))

Max Activating Token Index: 658

Text #3

Max Range: 4.0807. Min Range: -4.0807

Max Act: 3.9832. Min Act: -0.1700

Data Index: 1263778 (C4 (Web Text))

Max Activating Token Index: 291

Text #4

Max Range: 4.0807. Min Range: -4.0807

Max Act: 3.9298. Min Act: -0.1700

Data Index: 1271389 (C4 (Web Text))

Max Activating Token Index: 852

Text #5

Max Range: 4.0807. Min Range: -4.0807

Max Act: 3.9083. Min Act: -0.1700

Data Index: 65434 (C4 (Web Text))

Max Activating Token Index: 886

Text #6

Max Range: 4.0807. Min Range: -4.0807

Max Act: 3.8803. Min Act: -0.1699

Data Index: 880615 (C4 (Web Text))

Max Activating Token Index: 549

Text #7

Max Range: 4.0807. Min Range: -4.0807

Max Act: 3.8785. Min Act: -0.1700

Data Index: 1358044 (C4 (Web Text))

Max Activating Token Index: 22

Text #8

Max Range: 4.0807. Min Range: -4.0807

Max Act: 3.8403. Min Act: -0.1700

Data Index: 545826 (C4 (Web Text))

Max Activating Token Index: 531

Text #9

Max Range: 4.0807. Min Range: -4.0807

Max Act: 3.8520. Min Act: -0.1700

Data Index: 761450 (C4 (Web Text))

Max Activating Token Index: 305

Text #10

Max Range: 4.0807. Min Range: -4.0807

Max Act: 3.8333. Min Act: -0.1700

Data Index: 775526 (C4 (Web Text))

Max Activating Token Index: 479

Text #11

Max Range: 4.0807. Min Range: -4.0807

Max Act: 3.8316. Min Act: -0.1700

Data Index: 928997 (C4 (Web Text))

Max Activating Token Index: 764

Text #12

Max Range: 4.0807. Min Range: -4.0807

Max Act: 3.8245. Min Act: -0.1700

Data Index: 549462 (C4 (Web Text))

Max Activating Token Index: 764

Text #13

Max Range: 4.0807. Min Range: -4.0807

Max Act: 3.8396. Min Act: -0.1700

Data Index: 134752 (C4 (Web Text))

Max Activating Token Index: 723

Text #14

Max Range: 4.0807. Min Range: -4.0807

Max Act: 3.8167. Min Act: -0.1700

Data Index: 42615 (C4 (Web Text))

Max Activating Token Index: 808

Text #15

Max Range: 4.0807. Min Range: -4.0807

Max Act: 3.8165. Min Act: -0.1667

Data Index: 1338893 (C4 (Web Text))

Max Activating Token Index: 694

Text #16

Max Range: 4.0807. Min Range: -4.0807

Max Act: 3.7865. Min Act: -0.1700

Data Index: 318243 (C4 (Web Text))

Max Activating Token Index: 454

Text #17

Max Range: 4.0807. Min Range: -4.0807

Max Act: 3.7773. Min Act: -0.1700

Data Index: 662725 (C4 (Web Text))

Max Activating Token Index: 1004

Text #18

Max Range: 4.0807. Min Range: -4.0807

Max Act: 3.7827. Min Act: -0.1700

Data Index: 662315 (C4 (Web Text))

Max Activating Token Index: 956

Text #19

Max Range: 4.0807. Min Range: -4.0807

Max Act: 3.7773. Min Act: -0.1700

Data Index: 787800 (C4 (Web Text))

Max Activating Token Index: 972