Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 242 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 5.2737. Min Range: -5.2737

Max Act: 5.2737. Min Act: -0.1700

Data Index: 828582 (C4 (Web Text))

Max Activating Token Index: 499

Text #1

Max Range: 5.2737. Min Range: -5.2737

Max Act: 5.2424. Min Act: -0.1700

Data Index: 1312781 (C4 (Web Text))

Max Activating Token Index: 32

Text #2

Max Range: 5.2737. Min Range: -5.2737

Max Act: 5.1487. Min Act: -0.1700

Data Index: 298736 (C4 (Web Text))

Max Activating Token Index: 885

Text #3

Max Range: 5.2737. Min Range: -5.2737

Max Act: 5.2112. Min Act: -0.1700

Data Index: 290222 (C4 (Web Text))

Max Activating Token Index: 678

Text #4

Max Range: 5.2737. Min Range: -5.2737

Max Act: 5.0549. Min Act: -0.1700

Data Index: 1072636 (C4 (Web Text))

Max Activating Token Index: 544

Text #5

Max Range: 5.2737. Min Range: -5.2737

Max Act: 5.0237. Min Act: -0.1700

Data Index: 353694 (C4 (Web Text))

Max Activating Token Index: 234

Text #6

Max Range: 5.2737. Min Range: -5.2737

Max Act: 5.0549. Min Act: -0.1700

Data Index: 182768 (C4 (Web Text))

Max Activating Token Index: 939

Text #7

Max Range: 5.2737. Min Range: -5.2737

Max Act: 5.0549. Min Act: -0.1700

Data Index: 285508 (C4 (Web Text))

Max Activating Token Index: 115

Text #8

Max Range: 5.2737. Min Range: -5.2737

Max Act: 4.9612. Min Act: -0.1700

Data Index: 12876 (C4 (Web Text))

Max Activating Token Index: 638

Text #9

Max Range: 5.2737. Min Range: -5.2737

Max Act: 4.9924. Min Act: -0.1700

Data Index: 729948 (C4 (Web Text))

Max Activating Token Index: 912

Text #10

Max Range: 5.2737. Min Range: -5.2737

Max Act: 4.9612. Min Act: -0.1700

Data Index: 1112012 (C4 (Web Text))

Max Activating Token Index: 211

Text #11

Max Range: 5.2737. Min Range: -5.2737

Max Act: 4.9924. Min Act: -0.1700

Data Index: 103045 (C4 (Web Text))

Max Activating Token Index: 889

Text #12

Max Range: 5.2737. Min Range: -5.2737

Max Act: 5.0237. Min Act: -0.1700

Data Index: 717821 (C4 (Web Text))

Max Activating Token Index: 357

Text #13

Max Range: 5.2737. Min Range: -5.2737

Max Act: 4.9612. Min Act: -0.1700

Data Index: 401185 (C4 (Web Text))

Max Activating Token Index: 414

Text #14

Max Range: 5.2737. Min Range: -5.2737

Max Act: 4.9612. Min Act: -0.1700

Data Index: 351752 (C4 (Web Text))

Max Activating Token Index: 330

Text #15

Max Range: 5.2737. Min Range: -5.2737

Max Act: 4.9612. Min Act: -0.1700

Data Index: 908192 (C4 (Web Text))

Max Activating Token Index: 337

Text #16

Max Range: 5.2737. Min Range: -5.2737

Max Act: 4.9299. Min Act: -0.1700

Data Index: 650591 (C4 (Web Text))

Max Activating Token Index: 608

Text #17

Max Range: 5.2737. Min Range: -5.2737

Max Act: 4.8674. Min Act: -0.1700

Data Index: 905036 (C4 (Web Text))

Max Activating Token Index: 498

Text #18

Max Range: 5.2737. Min Range: -5.2737

Max Act: 4.8987. Min Act: -0.1700

Data Index: 1271929 (C4 (Web Text))

Max Activating Token Index: 862

Text #19

Max Range: 5.2737. Min Range: -5.2737

Max Act: 4.8674. Min Act: -0.1700

Data Index: 279250 (C4 (Web Text))

Max Activating Token Index: 844