Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 379 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 7.4767. Min Range: -7.4767

Max Act: 7.4767. Min Act: -0.1700

Data Index: 505183 (C4 (Web Text))

Max Activating Token Index: 390

Text #1

Max Range: 7.4767. Min Range: -7.4767

Max Act: 7.4767. Min Act: -0.1700

Data Index: 496243 (C4 (Web Text))

Max Activating Token Index: 565

Text #2

Max Range: 7.4767. Min Range: -7.4767

Max Act: 7.2892. Min Act: -0.1700

Data Index: 591346 (C4 (Web Text))

Max Activating Token Index: 547

Text #3

Max Range: 7.4767. Min Range: -7.4767

Max Act: 7.3517. Min Act: -0.1700

Data Index: 746415 (C4 (Web Text))

Max Activating Token Index: 385

Text #4

Max Range: 7.4767. Min Range: -7.4767

Max Act: 7.2892. Min Act: -0.1700

Data Index: 557018 (C4 (Web Text))

Max Activating Token Index: 54

Text #5

Max Range: 7.4767. Min Range: -7.4767

Max Act: 7.3517. Min Act: -0.1700

Data Index: 199746 (C4 (Web Text))

Max Activating Token Index: 163

Text #6

Max Range: 7.4767. Min Range: -7.4767

Max Act: 7.2267. Min Act: -0.1700

Data Index: 770909 (C4 (Web Text))

Max Activating Token Index: 179

Text #7

Max Range: 7.4767. Min Range: -7.4767

Max Act: 7.2892. Min Act: -0.1700

Data Index: 747120 (C4 (Web Text))

Max Activating Token Index: 630

Text #8

Max Range: 7.4767. Min Range: -7.4767

Max Act: 7.2267. Min Act: -0.1700

Data Index: 1050148 (C4 (Web Text))

Max Activating Token Index: 809

Text #9

Max Range: 7.4767. Min Range: -7.4767

Max Act: 7.2267. Min Act: -0.1700

Data Index: 169786 (C4 (Web Text))

Max Activating Token Index: 51

Text #10

Max Range: 7.4767. Min Range: -7.4767

Max Act: 7.2267. Min Act: -0.1700

Data Index: 673279 (C4 (Web Text))

Max Activating Token Index: 431

Text #11

Max Range: 7.4767. Min Range: -7.4767

Max Act: 7.2267. Min Act: -0.1700

Data Index: 1140797 (C4 (Web Text))

Max Activating Token Index: 437

Text #12

Max Range: 7.4767. Min Range: -7.4767

Max Act: 7.2267. Min Act: -0.1700

Data Index: 492602 (C4 (Web Text))

Max Activating Token Index: 332

Text #13

Max Range: 7.4767. Min Range: -7.4767

Max Act: 7.2267. Min Act: -0.1699

Data Index: 79946 (C4 (Web Text))

Max Activating Token Index: 590

Text #14

Max Range: 7.4767. Min Range: -7.4767

Max Act: 7.2267. Min Act: -0.1700

Data Index: 1196870 (C4 (Web Text))

Max Activating Token Index: 76

Text #15

Max Range: 7.4767. Min Range: -7.4767

Max Act: 7.2267. Min Act: -0.1700

Data Index: 746354 (C4 (Web Text))

Max Activating Token Index: 85

Text #16

Max Range: 7.4767. Min Range: -7.4767

Max Act: 7.1017. Min Act: -0.1700

Data Index: 611937 (C4 (Web Text))

Max Activating Token Index: 79

Text #17

Max Range: 7.4767. Min Range: -7.4767

Max Act: 7.2267. Min Act: -0.1700

Data Index: 85891 (C4 (Web Text))

Max Activating Token Index: 918

Text #18

Max Range: 7.4767. Min Range: -7.4767

Max Act: 7.1642. Min Act: -0.1700

Data Index: 620020 (C4 (Web Text))

Max Activating Token Index: 303

Text #19

Max Range: 7.4767. Min Range: -7.4767

Max Act: 7.1642. Min Act: -0.1700

Data Index: 827095 (C4 (Web Text))

Max Activating Token Index: 588