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

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

Neuron 602 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: 3.8876. Min Range: -3.8876

Max Act: 3.8876. Min Act: -0.1700

Data Index: 684798 (C4 (Web Text))

Max Activating Token Index: 521

Text #1

Max Range: 3.8876. Min Range: -3.8876

Max Act: 3.7938. Min Act: -0.1700

Data Index: 584456 (C4 (Web Text))

Max Activating Token Index: 218

Text #2

Max Range: 3.8876. Min Range: -3.8876

Max Act: 3.6373. Min Act: -0.1700

Data Index: 172052 (C4 (Web Text))

Max Activating Token Index: 842

Text #3

Max Range: 3.8876. Min Range: -3.8876

Max Act: 3.6999. Min Act: -0.1700

Data Index: 663778 (C4 (Web Text))

Max Activating Token Index: 889

Text #4

Max Range: 3.8876. Min Range: -3.8876

Max Act: 3.6999. Min Act: -0.1700

Data Index: 593157 (C4 (Web Text))

Max Activating Token Index: 305

Text #5

Max Range: 3.8876. Min Range: -3.8876

Max Act: 3.6999. Min Act: -0.1700

Data Index: 996522 (C4 (Web Text))

Max Activating Token Index: 823

Text #6

Max Range: 3.8876. Min Range: -3.8876

Max Act: 3.6999. Min Act: -0.1700

Data Index: 285775 (C4 (Web Text))

Max Activating Token Index: 927

Text #7

Max Range: 3.8876. Min Range: -3.8876

Max Act: 3.6373. Min Act: -0.1700

Data Index: 1266807 (C4 (Web Text))

Max Activating Token Index: 885

Text #8

Max Range: 3.8876. Min Range: -3.8876

Max Act: 3.6686. Min Act: -0.1700

Data Index: 1114071 (C4 (Web Text))

Max Activating Token Index: 928

Text #9

Max Range: 3.8876. Min Range: -3.8876

Max Act: 3.6999. Min Act: -0.1700

Data Index: 1026831 (C4 (Web Text))

Max Activating Token Index: 905

Text #10

Max Range: 3.8876. Min Range: -3.8876

Max Act: 3.5747. Min Act: -0.1700

Data Index: 408388 (C4 (Web Text))

Max Activating Token Index: 719

Text #11

Max Range: 3.8876. Min Range: -3.8876

Max Act: 3.6373. Min Act: -0.1700

Data Index: 39813 (C4 (Web Text))

Max Activating Token Index: 404

Text #12

Max Range: 3.8876. Min Range: -3.8876

Max Act: 3.6373. Min Act: -0.1700

Data Index: 1326679 (C4 (Web Text))

Max Activating Token Index: 259

Text #13

Max Range: 3.8876. Min Range: -3.8876

Max Act: 3.6373. Min Act: -0.1700

Data Index: 750470 (C4 (Web Text))

Max Activating Token Index: 872

Text #14

Max Range: 3.8876. Min Range: -3.8876

Max Act: 3.6373. Min Act: -0.1700

Data Index: 756757 (C4 (Web Text))

Max Activating Token Index: 905

Text #15

Max Range: 3.8876. Min Range: -3.8876

Max Act: 3.6373. Min Act: -0.1700

Data Index: 965158 (C4 (Web Text))

Max Activating Token Index: 366

Text #16

Max Range: 3.8876. Min Range: -3.8876

Max Act: 3.6373. Min Act: -0.1700

Data Index: 1300853 (C4 (Web Text))

Max Activating Token Index: 587

Text #17

Max Range: 3.8876. Min Range: -3.8876

Max Act: 3.6060. Min Act: -0.1700

Data Index: 671919 (C4 (Web Text))

Max Activating Token Index: 449

Text #18

Max Range: 3.8876. Min Range: -3.8876

Max Act: 3.6373. Min Act: -0.1700

Data Index: 1208502 (C4 (Web Text))

Max Activating Token Index: 175

Text #19

Max Range: 3.8876. Min Range: -3.8876

Max Act: 3.6373. Min Act: -0.1700

Data Index: 626314 (C4 (Web Text))

Max Activating Token Index: 553