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

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

Neuron 1715 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7793. Min Range: -3.7793

Max Act: 3.7793. Min Act: -0.1700

Data Index: 544600 (C4 (Web Text))

Max Activating Token Index: 819

Text #1

Max Range: 3.7793. Min Range: -3.7793

Max Act: 3.7480. Min Act: -0.1700

Data Index: 803760 (C4 (Web Text))

Max Activating Token Index: 619

Text #2

Max Range: 3.7793. Min Range: -3.7793

Max Act: 3.6854. Min Act: -0.1700

Data Index: 932275 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 3.7793. Min Range: -3.7793

Max Act: 3.6854. Min Act: -0.1700

Data Index: 202379 (C4 (Web Text))

Max Activating Token Index: 580

Text #4

Max Range: 3.7793. Min Range: -3.7793

Max Act: 3.6384. Min Act: -0.1700

Data Index: 144027 (C4 (Web Text))

Max Activating Token Index: 440

Text #5

Max Range: 3.7793. Min Range: -3.7793

Max Act: 3.6854. Min Act: -0.1700

Data Index: 445906 (C4 (Web Text))

Max Activating Token Index: 864

Text #6

Max Range: 3.7793. Min Range: -3.7793

Max Act: 3.6541. Min Act: -0.1700

Data Index: 893205 (C4 (Web Text))

Max Activating Token Index: 415

Text #7

Max Range: 3.7793. Min Range: -3.7793

Max Act: 3.6228. Min Act: -0.1700

Data Index: 578246 (C4 (Web Text))

Max Activating Token Index: 820

Text #8

Max Range: 3.7793. Min Range: -3.7793

Max Act: 3.6071. Min Act: -0.1700

Data Index: 849971 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 3.7793. Min Range: -3.7793

Max Act: 3.6228. Min Act: -0.1700

Data Index: 230477 (C4 (Web Text))

Max Activating Token Index: 370

Text #10

Max Range: 3.7793. Min Range: -3.7793

Max Act: 3.6071. Min Act: -0.1700

Data Index: 643369 (C4 (Web Text))

Max Activating Token Index: 590

Text #11

Max Range: 3.7793. Min Range: -3.7793

Max Act: 3.6384. Min Act: -0.1700

Data Index: 1280048 (C4 (Web Text))

Max Activating Token Index: 92

Text #12

Max Range: 3.7793. Min Range: -3.7793

Max Act: 3.5758. Min Act: -0.1700

Data Index: 1011259 (C4 (Web Text))

Max Activating Token Index: 1011

Text #13

Max Range: 3.7793. Min Range: -3.7793

Max Act: 3.5915. Min Act: -0.1700

Data Index: 1225635 (C4 (Web Text))

Max Activating Token Index: 702

Text #14

Max Range: 3.7793. Min Range: -3.7793

Max Act: 3.5132. Min Act: -0.1700

Data Index: 811296 (C4 (Web Text))

Max Activating Token Index: 983

Text #15

Max Range: 3.7793. Min Range: -3.7793

Max Act: 3.6071. Min Act: -0.1700

Data Index: 262170 (C4 (Web Text))

Max Activating Token Index: 680

Text #16

Max Range: 3.7793. Min Range: -3.7793

Max Act: 3.5758. Min Act: -0.1700

Data Index: 102857 (C4 (Web Text))

Max Activating Token Index: 635

Text #17

Max Range: 3.7793. Min Range: -3.7793

Max Act: 3.5915. Min Act: -0.1700

Data Index: 320913 (C4 (Web Text))

Max Activating Token Index: 246

Text #18

Max Range: 3.7793. Min Range: -3.7793

Max Act: 3.5915. Min Act: -0.1700

Data Index: 945233 (C4 (Web Text))

Max Activating Token Index: 767

Text #19

Max Range: 3.7793. Min Range: -3.7793

Max Act: 3.5758. Min Act: -0.1700

Data Index: 956089 (C4 (Web Text))

Max Activating Token Index: 71