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

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

Neuron 372 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3908. Min Range: -3.3908

Max Act: 3.3908. Min Act: -0.1700

Data Index: 403080 (C4 (Web Text))

Max Activating Token Index: 822

Text #1

Max Range: 3.3908. Min Range: -3.3908

Max Act: 3.3437. Min Act: -0.1700

Data Index: 621547 (C4 (Web Text))

Max Activating Token Index: 567

Text #2

Max Range: 3.3908. Min Range: -3.3908

Max Act: 3.3594. Min Act: -0.1700

Data Index: 346729 (C4 (Web Text))

Max Activating Token Index: 757

Text #3

Max Range: 3.3908. Min Range: -3.3908

Max Act: 3.3594. Min Act: -0.1700

Data Index: 177895 (C4 (Web Text))

Max Activating Token Index: 924

Text #4

Max Range: 3.3908. Min Range: -3.3908

Max Act: 3.3280. Min Act: -0.1700

Data Index: 582528 (C4 (Web Text))

Max Activating Token Index: 603

Text #5

Max Range: 3.3908. Min Range: -3.3908

Max Act: 3.3437. Min Act: -0.1700

Data Index: 1170162 (C4 (Web Text))

Max Activating Token Index: 225

Text #6

Max Range: 3.3908. Min Range: -3.3908

Max Act: 3.2966. Min Act: -0.1700

Data Index: 710292 (C4 (Web Text))

Max Activating Token Index: 496

Text #7

Max Range: 3.3908. Min Range: -3.3908

Max Act: 3.2652. Min Act: -0.1700

Data Index: 375772 (C4 (Web Text))

Max Activating Token Index: 730

Text #8

Max Range: 3.3908. Min Range: -3.3908

Max Act: 3.3280. Min Act: -0.1700

Data Index: 183174 (C4 (Web Text))

Max Activating Token Index: 678

Text #9

Max Range: 3.3908. Min Range: -3.3908

Max Act: 3.3123. Min Act: -0.1700

Data Index: 618264 (C4 (Web Text))

Max Activating Token Index: 765

Text #10

Max Range: 3.3908. Min Range: -3.3908

Max Act: 3.3123. Min Act: -0.1700

Data Index: 226049 (C4 (Web Text))

Max Activating Token Index: 643

Text #11

Max Range: 3.3908. Min Range: -3.3908

Max Act: 3.3123. Min Act: -0.1700

Data Index: 98582 (C4 (Web Text))

Max Activating Token Index: 955

Text #12

Max Range: 3.3908. Min Range: -3.3908

Max Act: 3.3123. Min Act: -0.1700

Data Index: 717497 (C4 (Web Text))

Max Activating Token Index: 883

Text #13

Max Range: 3.3908. Min Range: -3.3908

Max Act: 3.2966. Min Act: -0.1700

Data Index: 638771 (C4 (Web Text))

Max Activating Token Index: 334

Text #14

Max Range: 3.3908. Min Range: -3.3908

Max Act: 3.2652. Min Act: -0.1700

Data Index: 109444 (C4 (Web Text))

Max Activating Token Index: 440

Text #15

Max Range: 3.3908. Min Range: -3.3908

Max Act: 3.2809. Min Act: -0.1700

Data Index: 157296 (C4 (Web Text))

Max Activating Token Index: 215

Text #16

Max Range: 3.3908. Min Range: -3.3908

Max Act: 3.2809. Min Act: -0.1700

Data Index: 295882 (C4 (Web Text))

Max Activating Token Index: 914

Text #17

Max Range: 3.3908. Min Range: -3.3908

Max Act: 3.2809. Min Act: -0.1700

Data Index: 452431 (C4 (Web Text))

Max Activating Token Index: 816

Text #18

Max Range: 3.3908. Min Range: -3.3908

Max Act: 3.2809. Min Act: -0.1700

Data Index: 119700 (C4 (Web Text))

Max Activating Token Index: 769

Text #19

Max Range: 3.3908. Min Range: -3.3908

Max Act: 3.2652. Min Act: -0.1700

Data Index: 464555 (C4 (Web Text))

Max Activating Token Index: 270