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

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

Neuron 136 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: 3.3507. Min Range: -3.3507

Max Act: 3.3507. Min Act: -0.1700

Data Index: 731769 (C4 (Web Text))

Max Activating Token Index: 718

Text #1

Max Range: 3.3507. Min Range: -3.3507

Max Act: 3.2228. Min Act: -0.1700

Data Index: 130398 (C4 (Web Text))

Max Activating Token Index: 663

Text #2

Max Range: 3.3507. Min Range: -3.3507

Max Act: 3.1385. Min Act: -0.1700

Data Index: 647774 (C4 (Web Text))

Max Activating Token Index: 308

Text #3

Max Range: 3.3507. Min Range: -3.3507

Max Act: 3.1055. Min Act: -0.1699

Data Index: 1266097 (C4 (Web Text))

Max Activating Token Index: 779

Text #4

Max Range: 3.3507. Min Range: -3.3507

Max Act: 3.1080. Min Act: -0.1700

Data Index: 837898 (C4 (Web Text))

Max Activating Token Index: 627

Text #5

Max Range: 3.3507. Min Range: -3.3507

Max Act: 3.0945. Min Act: -0.1700

Data Index: 52721 (C4 (Web Text))

Max Activating Token Index: 551

Text #6

Max Range: 3.3507. Min Range: -3.3507

Max Act: 3.0770. Min Act: -0.1700

Data Index: 911278 (C4 (Web Text))

Max Activating Token Index: 1002

Text #7

Max Range: 3.3507. Min Range: -3.3507

Max Act: 3.0793. Min Act: -0.1700

Data Index: 192532 (C4 (Web Text))

Max Activating Token Index: 688

Text #8

Max Range: 3.3507. Min Range: -3.3507

Max Act: 3.0828. Min Act: -0.1700

Data Index: 243619 (C4 (Web Text))

Max Activating Token Index: 736

Text #9

Max Range: 3.3507. Min Range: -3.3507

Max Act: 3.0688. Min Act: -0.1700

Data Index: 481498 (C4 (Web Text))

Max Activating Token Index: 340

Text #10

Max Range: 3.3507. Min Range: -3.3507

Max Act: 3.0781. Min Act: -0.1641

Data Index: 575853 (C4 (Web Text))

Max Activating Token Index: 242

Text #11

Max Range: 3.3507. Min Range: -3.3507

Max Act: 3.0559. Min Act: -0.1700

Data Index: 1279503 (C4 (Web Text))

Max Activating Token Index: 808

Text #12

Max Range: 3.3507. Min Range: -3.3507

Max Act: 3.0615. Min Act: -0.1700

Data Index: 964399 (C4 (Web Text))

Max Activating Token Index: 311

Text #13

Max Range: 3.3507. Min Range: -3.3507

Max Act: 3.0639. Min Act: -0.1698

Data Index: 1077809 (C4 (Web Text))

Max Activating Token Index: 67

Text #14

Max Range: 3.3507. Min Range: -3.3507

Max Act: 3.0503. Min Act: -0.1700

Data Index: 228624 (C4 (Web Text))

Max Activating Token Index: 717

Text #15

Max Range: 3.3507. Min Range: -3.3507

Max Act: 3.0509. Min Act: -0.1696

Data Index: 651817 (C4 (Web Text))

Max Activating Token Index: 823

Text #16

Max Range: 3.3507. Min Range: -3.3507

Max Act: 3.0395. Min Act: -0.1700

Data Index: 1376760 (Python Code)

Max Activating Token Index: 37

Text #17

Max Range: 3.3507. Min Range: -3.3507

Max Act: 3.0529. Min Act: -0.1700

Data Index: 109645 (C4 (Web Text))

Max Activating Token Index: 940

Text #18

Max Range: 3.3507. Min Range: -3.3507

Max Act: 3.0309. Min Act: -0.1696

Data Index: 730954 (C4 (Web Text))

Max Activating Token Index: 699

Text #19

Max Range: 3.3507. Min Range: -3.3507

Max Act: 3.0443. Min Act: -0.1700

Data Index: 722284 (C4 (Web Text))

Max Activating Token Index: 112