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

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

Neuron 474 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.2718. Min Range: -5.2718

Max Act: 5.2718. Min Act: -0.1700

Data Index: 1217463 (C4 (Web Text))

Max Activating Token Index: 722

Text #1

Max Range: 5.2718. Min Range: -5.2718

Max Act: 5.2405. Min Act: -0.1700

Data Index: 79153 (C4 (Web Text))

Max Activating Token Index: 572

Text #2

Max Range: 5.2718. Min Range: -5.2718

Max Act: 5.1780. Min Act: -0.1700

Data Index: 685655 (C4 (Web Text))

Max Activating Token Index: 615

Text #3

Max Range: 5.2718. Min Range: -5.2718

Max Act: 5.0843. Min Act: -0.1700

Data Index: 764439 (C4 (Web Text))

Max Activating Token Index: 682

Text #4

Max Range: 5.2718. Min Range: -5.2718

Max Act: 5.1155. Min Act: -0.1700

Data Index: 303667 (C4 (Web Text))

Max Activating Token Index: 775

Text #5

Max Range: 5.2718. Min Range: -5.2718

Max Act: 5.1155. Min Act: -0.1700

Data Index: 1065416 (C4 (Web Text))

Max Activating Token Index: 992

Text #6

Max Range: 5.2718. Min Range: -5.2718

Max Act: 5.1155. Min Act: -0.1700

Data Index: 934603 (C4 (Web Text))

Max Activating Token Index: 650

Text #7

Max Range: 5.2718. Min Range: -5.2718

Max Act: 5.0218. Min Act: -0.1700

Data Index: 1086995 (C4 (Web Text))

Max Activating Token Index: 716

Text #8

Max Range: 5.2718. Min Range: -5.2718

Max Act: 4.9905. Min Act: -0.1700

Data Index: 92302 (C4 (Web Text))

Max Activating Token Index: 666

Text #9

Max Range: 5.2718. Min Range: -5.2718

Max Act: 5.0530. Min Act: -0.1700

Data Index: 213664 (C4 (Web Text))

Max Activating Token Index: 371

Text #10

Max Range: 5.2718. Min Range: -5.2718

Max Act: 4.9905. Min Act: -0.1700

Data Index: 1077218 (C4 (Web Text))

Max Activating Token Index: 895

Text #11

Max Range: 5.2718. Min Range: -5.2718

Max Act: 5.0530. Min Act: -0.1700

Data Index: 1134320 (C4 (Web Text))

Max Activating Token Index: 785

Text #12

Max Range: 5.2718. Min Range: -5.2718

Max Act: 4.9905. Min Act: -0.1700

Data Index: 1322902 (C4 (Web Text))

Max Activating Token Index: 554

Text #13

Max Range: 5.2718. Min Range: -5.2718

Max Act: 4.9280. Min Act: -0.1700

Data Index: 918403 (C4 (Web Text))

Max Activating Token Index: 337

Text #14

Max Range: 5.2718. Min Range: -5.2718

Max Act: 4.9280. Min Act: -0.1700

Data Index: 667032 (C4 (Web Text))

Max Activating Token Index: 919

Text #15

Max Range: 5.2718. Min Range: -5.2718

Max Act: 4.9280. Min Act: -0.1700

Data Index: 220119 (C4 (Web Text))

Max Activating Token Index: 433

Text #16

Max Range: 5.2718. Min Range: -5.2718

Max Act: 5.0530. Min Act: -0.1700

Data Index: 1223727 (C4 (Web Text))

Max Activating Token Index: 428

Text #17

Max Range: 5.2718. Min Range: -5.2718

Max Act: 4.8968. Min Act: -0.1700

Data Index: 405258 (C4 (Web Text))

Max Activating Token Index: 443

Text #18

Max Range: 5.2718. Min Range: -5.2718

Max Act: 4.9280. Min Act: -0.1700

Data Index: 805454 (C4 (Web Text))

Max Activating Token Index: 84

Text #19

Max Range: 5.2718. Min Range: -5.2718

Max Act: 4.9593. Min Act: -0.1700

Data Index: 599625 (C4 (Web Text))

Max Activating Token Index: 862