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

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

Neuron 1100 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: 3.8372. Min Range: -3.8372

Max Act: 3.7433. Min Act: -0.1700

Data Index: 736928 (C4 (Web Text))

Max Activating Token Index: 893

Text #1

Max Range: 3.8372. Min Range: -3.8372

Max Act: 3.7746. Min Act: -0.1700

Data Index: 1249383 (C4 (Web Text))

Max Activating Token Index: 1008

Text #2

Max Range: 3.8372. Min Range: -3.8372

Max Act: 3.7120. Min Act: -0.1700

Data Index: 1313354 (C4 (Web Text))

Max Activating Token Index: 1001

Text #3

Max Range: 3.8372. Min Range: -3.8372

Max Act: 3.8372. Min Act: -0.1700

Data Index: 307029 (C4 (Web Text))

Max Activating Token Index: 825

Text #4

Max Range: 3.8372. Min Range: -3.8372

Max Act: 3.6807. Min Act: -0.1700

Data Index: 616906 (C4 (Web Text))

Max Activating Token Index: 1009

Text #5

Max Range: 3.8372. Min Range: -3.8372

Max Act: 3.7433. Min Act: -0.1700

Data Index: 978911 (C4 (Web Text))

Max Activating Token Index: 627

Text #6

Max Range: 3.8372. Min Range: -3.8372

Max Act: 3.6807. Min Act: -0.1700

Data Index: 321048 (C4 (Web Text))

Max Activating Token Index: 769

Text #7

Max Range: 3.8372. Min Range: -3.8372

Max Act: 3.6494. Min Act: -0.1700

Data Index: 674534 (C4 (Web Text))

Max Activating Token Index: 163

Text #8

Max Range: 3.8372. Min Range: -3.8372

Max Act: 3.6494. Min Act: -0.1700

Data Index: 699925 (C4 (Web Text))

Max Activating Token Index: 920

Text #9

Max Range: 3.8372. Min Range: -3.8372

Max Act: 3.6807. Min Act: -0.1700

Data Index: 314183 (C4 (Web Text))

Max Activating Token Index: 748

Text #10

Max Range: 3.8372. Min Range: -3.8372

Max Act: 3.6494. Min Act: -0.1700

Data Index: 1321145 (C4 (Web Text))

Max Activating Token Index: 332

Text #11

Max Range: 3.8372. Min Range: -3.8372

Max Act: 3.6494. Min Act: -0.1700

Data Index: 187584 (C4 (Web Text))

Max Activating Token Index: 761

Text #12

Max Range: 3.8372. Min Range: -3.8372

Max Act: 3.6181. Min Act: -0.1700

Data Index: 320630 (C4 (Web Text))

Max Activating Token Index: 103

Text #13

Max Range: 3.8372. Min Range: -3.8372

Max Act: 3.6181. Min Act: -0.1700

Data Index: 962911 (C4 (Web Text))

Max Activating Token Index: 913

Text #14

Max Range: 3.8372. Min Range: -3.8372

Max Act: 3.6181. Min Act: -0.1700

Data Index: 737561 (C4 (Web Text))

Max Activating Token Index: 930

Text #15

Max Range: 3.8372. Min Range: -3.8372

Max Act: 3.6181. Min Act: -0.1700

Data Index: 347286 (C4 (Web Text))

Max Activating Token Index: 696

Text #16

Max Range: 3.8372. Min Range: -3.8372

Max Act: 3.6807. Min Act: -0.1700

Data Index: 578699 (C4 (Web Text))

Max Activating Token Index: 362

Text #17

Max Range: 3.8372. Min Range: -3.8372

Max Act: 3.6494. Min Act: -0.1700

Data Index: 1216028 (C4 (Web Text))

Max Activating Token Index: 814

Text #18

Max Range: 3.8372. Min Range: -3.8372

Max Act: 3.6807. Min Act: -0.1700

Data Index: 1108775 (C4 (Web Text))

Max Activating Token Index: 5

Text #19

Max Range: 3.8372. Min Range: -3.8372

Max Act: 3.5868. Min Act: -0.1700

Data Index: 725677 (C4 (Web Text))

Max Activating Token Index: 661