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

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

Neuron 573 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: 7.2751. Min Range: -7.2751

Max Act: 7.2751. Min Act: -0.1700

Data Index: 591548 (C4 (Web Text))

Max Activating Token Index: 349

Text #1

Max Range: 7.2751. Min Range: -7.2751

Max Act: 7.0251. Min Act: -0.1700

Data Index: 1261154 (C4 (Web Text))

Max Activating Token Index: 832

Text #2

Max Range: 7.2751. Min Range: -7.2751

Max Act: 7.0251. Min Act: -0.1700

Data Index: 505604 (C4 (Web Text))

Max Activating Token Index: 645

Text #3

Max Range: 7.2751. Min Range: -7.2751

Max Act: 6.9626. Min Act: -0.1700

Data Index: 855228 (C4 (Web Text))

Max Activating Token Index: 298

Text #4

Max Range: 7.2751. Min Range: -7.2751

Max Act: 6.9626. Min Act: -0.1700

Data Index: 675815 (C4 (Web Text))

Max Activating Token Index: 167

Text #5

Max Range: 7.2751. Min Range: -7.2751

Max Act: 6.9001. Min Act: -0.1700

Data Index: 1067557 (C4 (Web Text))

Max Activating Token Index: 324

Text #6

Max Range: 7.2751. Min Range: -7.2751

Max Act: 6.9001. Min Act: -0.1700

Data Index: 748791 (C4 (Web Text))

Max Activating Token Index: 583

Text #7

Max Range: 7.2751. Min Range: -7.2751

Max Act: 6.8376. Min Act: -0.1700

Data Index: 1340055 (C4 (Web Text))

Max Activating Token Index: 655

Text #8

Max Range: 7.2751. Min Range: -7.2751

Max Act: 6.8376. Min Act: -0.1699

Data Index: 204044 (C4 (Web Text))

Max Activating Token Index: 821

Text #9

Max Range: 7.2751. Min Range: -7.2751

Max Act: 6.7126. Min Act: -0.1700

Data Index: 450457 (C4 (Web Text))

Max Activating Token Index: 568

Text #10

Max Range: 7.2751. Min Range: -7.2751

Max Act: 6.8376. Min Act: -0.1700

Data Index: 1264818 (C4 (Web Text))

Max Activating Token Index: 804

Text #11

Max Range: 7.2751. Min Range: -7.2751

Max Act: 6.8376. Min Act: -0.1700

Data Index: 123358 (C4 (Web Text))

Max Activating Token Index: 893

Text #12

Max Range: 7.2751. Min Range: -7.2751

Max Act: 6.8376. Min Act: -0.1700

Data Index: 31858 (C4 (Web Text))

Max Activating Token Index: 468

Text #13

Max Range: 7.2751. Min Range: -7.2751

Max Act: 6.8376. Min Act: -0.1700

Data Index: 82373 (C4 (Web Text))

Max Activating Token Index: 784

Text #14

Max Range: 7.2751. Min Range: -7.2751

Max Act: 6.8376. Min Act: -0.1700

Data Index: 61087 (C4 (Web Text))

Max Activating Token Index: 827

Text #15

Max Range: 7.2751. Min Range: -7.2751

Max Act: 6.7751. Min Act: -0.1700

Data Index: 891823 (C4 (Web Text))

Max Activating Token Index: 863

Text #16

Max Range: 7.2751. Min Range: -7.2751

Max Act: 6.8376. Min Act: -0.1700

Data Index: 12602 (C4 (Web Text))

Max Activating Token Index: 127

Text #17

Max Range: 7.2751. Min Range: -7.2751

Max Act: 6.8376. Min Act: -0.1700

Data Index: 423671 (C4 (Web Text))

Max Activating Token Index: 42

Text #18

Max Range: 7.2751. Min Range: -7.2751

Max Act: 6.8376. Min Act: -0.1700

Data Index: 998049 (C4 (Web Text))

Max Activating Token Index: 800

Text #19

Max Range: 7.2751. Min Range: -7.2751

Max Act: 6.8376. Min Act: -0.1700

Data Index: 380771 (C4 (Web Text))

Max Activating Token Index: 48