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

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

Neuron 241 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: 4.6856. Min Range: -4.6856

Max Act: 4.6856. Min Act: -0.1700

Data Index: 1019080 (C4 (Web Text))

Max Activating Token Index: 499

Text #1

Max Range: 4.6856. Min Range: -4.6856

Max Act: 4.6119. Min Act: -0.1700

Data Index: 683914 (C4 (Web Text))

Max Activating Token Index: 697

Text #2

Max Range: 4.6856. Min Range: -4.6856

Max Act: 4.5613. Min Act: -0.1700

Data Index: 303739 (C4 (Web Text))

Max Activating Token Index: 967

Text #3

Max Range: 4.6856. Min Range: -4.6856

Max Act: 4.6064. Min Act: -0.1700

Data Index: 914631 (C4 (Web Text))

Max Activating Token Index: 397

Text #4

Max Range: 4.6856. Min Range: -4.6856

Max Act: 4.5775. Min Act: -0.1700

Data Index: 530101 (C4 (Web Text))

Max Activating Token Index: 114

Text #5

Max Range: 4.6856. Min Range: -4.6856

Max Act: 4.5251. Min Act: -0.1700

Data Index: 641752 (C4 (Web Text))

Max Activating Token Index: 787

Text #6

Max Range: 4.6856. Min Range: -4.6856

Max Act: 4.5133. Min Act: -0.1700

Data Index: 522503 (C4 (Web Text))

Max Activating Token Index: 557

Text #7

Max Range: 4.6856. Min Range: -4.6856

Max Act: 4.5677. Min Act: -0.1700

Data Index: 1018587 (C4 (Web Text))

Max Activating Token Index: 340

Text #8

Max Range: 4.6856. Min Range: -4.6856

Max Act: 4.5510. Min Act: -0.1700

Data Index: 465710 (C4 (Web Text))

Max Activating Token Index: 586

Text #9

Max Range: 4.6856. Min Range: -4.6856

Max Act: 4.5374. Min Act: -0.1700

Data Index: 1092399 (C4 (Web Text))

Max Activating Token Index: 618

Text #10

Max Range: 4.6856. Min Range: -4.6856

Max Act: 4.5695. Min Act: -0.1700

Data Index: 1130973 (C4 (Web Text))

Max Activating Token Index: 67

Text #11

Max Range: 4.6856. Min Range: -4.6856

Max Act: 4.5343. Min Act: -0.1700

Data Index: 1153330 (C4 (Web Text))

Max Activating Token Index: 664

Text #12

Max Range: 4.6856. Min Range: -4.6856

Max Act: 4.5024. Min Act: -0.1700

Data Index: 1172825 (C4 (Web Text))

Max Activating Token Index: 315

Text #13

Max Range: 4.6856. Min Range: -4.6856

Max Act: 4.5290. Min Act: -0.1700

Data Index: 170302 (C4 (Web Text))

Max Activating Token Index: 333

Text #14

Max Range: 4.6856. Min Range: -4.6856

Max Act: 4.4726. Min Act: -0.1700

Data Index: 1045341 (C4 (Web Text))

Max Activating Token Index: 600

Text #15

Max Range: 4.6856. Min Range: -4.6856

Max Act: 4.4816. Min Act: -0.1700

Data Index: 717710 (C4 (Web Text))

Max Activating Token Index: 498

Text #16

Max Range: 4.6856. Min Range: -4.6856

Max Act: 4.4838. Min Act: -0.1700

Data Index: 248641 (C4 (Web Text))

Max Activating Token Index: 568

Text #17

Max Range: 4.6856. Min Range: -4.6856

Max Act: 4.5023. Min Act: -0.1700

Data Index: 247477 (C4 (Web Text))

Max Activating Token Index: 603

Text #18

Max Range: 4.6856. Min Range: -4.6856

Max Act: 4.4986. Min Act: -0.1700

Data Index: 241720 (C4 (Web Text))

Max Activating Token Index: 450

Text #19

Max Range: 4.6856. Min Range: -4.6856

Max Act: 4.4716. Min Act: -0.1700

Data Index: 405301 (C4 (Web Text))

Max Activating Token Index: 935