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

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

Neuron 685 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: 3.9473. Min Range: -3.9473

Max Act: 3.9473. Min Act: -0.1700

Data Index: 250454 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 3.9473. Min Range: -3.9473

Max Act: 3.8222. Min Act: -0.1700

Data Index: 1345959 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 3.9473. Min Range: -3.9473

Max Act: 3.6971. Min Act: -0.1700

Data Index: 1015368 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 3.9473. Min Range: -3.9473

Max Act: 3.5719. Min Act: -0.1700

Data Index: 1211897 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 3.9473. Min Range: -3.9473

Max Act: 3.6032. Min Act: -0.1700

Data Index: 8158 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 3.9473. Min Range: -3.9473

Max Act: 3.5092. Min Act: -0.1700

Data Index: 1148817 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 3.9473. Min Range: -3.9473

Max Act: 3.4779. Min Act: -0.1700

Data Index: 850597 (C4 (Web Text))

Max Activating Token Index: 773

Text #7

Max Range: 3.9473. Min Range: -3.9473

Max Act: 3.4465. Min Act: -0.1700

Data Index: 527637 (C4 (Web Text))

Max Activating Token Index: 12

Text #8

Max Range: 3.9473. Min Range: -3.9473

Max Act: 3.4465. Min Act: -0.1700

Data Index: 292422 (C4 (Web Text))

Max Activating Token Index: 828

Text #9

Max Range: 3.9473. Min Range: -3.9473

Max Act: 3.4308. Min Act: -0.1700

Data Index: 1423419 (Python Code)

Max Activating Token Index: 1023

Text #10

Max Range: 3.9473. Min Range: -3.9473

Max Act: 3.4151. Min Act: -0.1700

Data Index: 150391 (C4 (Web Text))

Max Activating Token Index: 42

Text #11

Max Range: 3.9473. Min Range: -3.9473

Max Act: 3.3995. Min Act: -0.1700

Data Index: 217177 (C4 (Web Text))

Max Activating Token Index: 811

Text #12

Max Range: 3.9473. Min Range: -3.9473

Max Act: 3.3838. Min Act: -0.1700

Data Index: 36748 (C4 (Web Text))

Max Activating Token Index: 904

Text #13

Max Range: 3.9473. Min Range: -3.9473

Max Act: 3.4151. Min Act: -0.1700

Data Index: 705350 (C4 (Web Text))

Max Activating Token Index: 830

Text #14

Max Range: 3.9473. Min Range: -3.9473

Max Act: 3.3838. Min Act: -0.1700

Data Index: 647742 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 3.9473. Min Range: -3.9473

Max Act: 3.3838. Min Act: -0.1700

Data Index: 653827 (C4 (Web Text))

Max Activating Token Index: 957

Text #16

Max Range: 3.9473. Min Range: -3.9473

Max Act: 3.3838. Min Act: -0.1700

Data Index: 32673 (C4 (Web Text))

Max Activating Token Index: 268

Text #17

Max Range: 3.9473. Min Range: -3.9473

Max Act: 3.3995. Min Act: -0.1700

Data Index: 178125 (C4 (Web Text))

Max Activating Token Index: 347

Text #18

Max Range: 3.9473. Min Range: -3.9473

Max Act: 3.3995. Min Act: -0.1700

Data Index: 686193 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 3.9473. Min Range: -3.9473

Max Act: 3.3838. Min Act: -0.1700

Data Index: 1108598 (C4 (Web Text))

Max Activating Token Index: 483