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

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

Neuron 638 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: 5.0588. Min Range: -5.0588

Max Act: 5.0588. Min Act: -0.1700

Data Index: 135631 (C4 (Web Text))

Max Activating Token Index: 530

Text #1

Max Range: 5.0588. Min Range: -5.0588

Max Act: 4.9963. Min Act: -0.1700

Data Index: 824910 (C4 (Web Text))

Max Activating Token Index: 816

Text #2

Max Range: 5.0588. Min Range: -5.0588

Max Act: 5.0275. Min Act: -0.1700

Data Index: 367069 (C4 (Web Text))

Max Activating Token Index: 400

Text #3

Max Range: 5.0588. Min Range: -5.0588

Max Act: 4.9338. Min Act: -0.1700

Data Index: 651791 (C4 (Web Text))

Max Activating Token Index: 361

Text #4

Max Range: 5.0588. Min Range: -5.0588

Max Act: 4.9338. Min Act: -0.1700

Data Index: 233645 (C4 (Web Text))

Max Activating Token Index: 837

Text #5

Max Range: 5.0588. Min Range: -5.0588

Max Act: 4.8400. Min Act: -0.1700

Data Index: 653049 (C4 (Web Text))

Max Activating Token Index: 658

Text #6

Max Range: 5.0588. Min Range: -5.0588

Max Act: 4.8088. Min Act: -0.1700

Data Index: 703602 (C4 (Web Text))

Max Activating Token Index: 967

Text #7

Max Range: 5.0588. Min Range: -5.0588

Max Act: 4.8400. Min Act: -0.1700

Data Index: 1222126 (C4 (Web Text))

Max Activating Token Index: 467

Text #8

Max Range: 5.0588. Min Range: -5.0588

Max Act: 4.8088. Min Act: -0.1700

Data Index: 1148783 (C4 (Web Text))

Max Activating Token Index: 356

Text #9

Max Range: 5.0588. Min Range: -5.0588

Max Act: 4.8088. Min Act: -0.1700

Data Index: 513290 (C4 (Web Text))

Max Activating Token Index: 563

Text #10

Max Range: 5.0588. Min Range: -5.0588

Max Act: 4.8088. Min Act: -0.1700

Data Index: 598382 (C4 (Web Text))

Max Activating Token Index: 699

Text #11

Max Range: 5.0588. Min Range: -5.0588

Max Act: 4.7463. Min Act: -0.1700

Data Index: 1279177 (C4 (Web Text))

Max Activating Token Index: 410

Text #12

Max Range: 5.0588. Min Range: -5.0588

Max Act: 4.7463. Min Act: -0.1700

Data Index: 886562 (C4 (Web Text))

Max Activating Token Index: 701

Text #13

Max Range: 5.0588. Min Range: -5.0588

Max Act: 4.6838. Min Act: -0.1700

Data Index: 277616 (C4 (Web Text))

Max Activating Token Index: 238

Text #14

Max Range: 5.0588. Min Range: -5.0588

Max Act: 4.7150. Min Act: -0.1700

Data Index: 993746 (C4 (Web Text))

Max Activating Token Index: 806

Text #15

Max Range: 5.0588. Min Range: -5.0588

Max Act: 4.6838. Min Act: -0.1700

Data Index: 879416 (C4 (Web Text))

Max Activating Token Index: 812

Text #16

Max Range: 5.0588. Min Range: -5.0588

Max Act: 4.6525. Min Act: -0.1700

Data Index: 734970 (C4 (Web Text))

Max Activating Token Index: 803

Text #17

Max Range: 5.0588. Min Range: -5.0588

Max Act: 4.6525. Min Act: -0.1698

Data Index: 1165283 (C4 (Web Text))

Max Activating Token Index: 560

Text #18

Max Range: 5.0588. Min Range: -5.0588

Max Act: 4.6838. Min Act: -0.1700

Data Index: 884581 (C4 (Web Text))

Max Activating Token Index: 687

Text #19

Max Range: 5.0588. Min Range: -5.0588

Max Act: 4.6838. Min Act: -0.1700

Data Index: 456655 (C4 (Web Text))

Max Activating Token Index: 312