Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 903 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.7364. Min Range: -3.7364

Max Act: 3.7364. Min Act: -0.1700

Data Index: 313467 (C4 (Web Text))

Max Activating Token Index: 794

Text #1

Max Range: 3.7364. Min Range: -3.7364

Max Act: 3.7051. Min Act: -0.1700

Data Index: 208662 (C4 (Web Text))

Max Activating Token Index: 720

Text #2

Max Range: 3.7364. Min Range: -3.7364

Max Act: 3.7051. Min Act: -0.1700

Data Index: 109545 (C4 (Web Text))

Max Activating Token Index: 93

Text #3

Max Range: 3.7364. Min Range: -3.7364

Max Act: 3.6738. Min Act: -0.1700

Data Index: 886343 (C4 (Web Text))

Max Activating Token Index: 856

Text #4

Max Range: 3.7364. Min Range: -3.7364

Max Act: 3.6738. Min Act: -0.1700

Data Index: 1290868 (C4 (Web Text))

Max Activating Token Index: 838

Text #5

Max Range: 3.7364. Min Range: -3.7364

Max Act: 3.7051. Min Act: -0.1700

Data Index: 86314 (C4 (Web Text))

Max Activating Token Index: 718

Text #6

Max Range: 3.7364. Min Range: -3.7364

Max Act: 3.6738. Min Act: -0.1700

Data Index: 81730 (C4 (Web Text))

Max Activating Token Index: 356

Text #7

Max Range: 3.7364. Min Range: -3.7364

Max Act: 3.6738. Min Act: -0.1700

Data Index: 770356 (C4 (Web Text))

Max Activating Token Index: 833

Text #8

Max Range: 3.7364. Min Range: -3.7364

Max Act: 3.6425. Min Act: -0.1700

Data Index: 1325194 (C4 (Web Text))

Max Activating Token Index: 338

Text #9

Max Range: 3.7364. Min Range: -3.7364

Max Act: 3.6112. Min Act: -0.1700

Data Index: 930447 (C4 (Web Text))

Max Activating Token Index: 755

Text #10

Max Range: 3.7364. Min Range: -3.7364

Max Act: 3.6738. Min Act: -0.1700

Data Index: 948802 (C4 (Web Text))

Max Activating Token Index: 732

Text #11

Max Range: 3.7364. Min Range: -3.7364

Max Act: 3.6425. Min Act: -0.1700

Data Index: 895395 (C4 (Web Text))

Max Activating Token Index: 293

Text #12

Max Range: 3.7364. Min Range: -3.7364

Max Act: 3.6425. Min Act: -0.1700

Data Index: 511611 (C4 (Web Text))

Max Activating Token Index: 803

Text #13

Max Range: 3.7364. Min Range: -3.7364

Max Act: 3.6112. Min Act: -0.1700

Data Index: 630361 (C4 (Web Text))

Max Activating Token Index: 357

Text #14

Max Range: 3.7364. Min Range: -3.7364

Max Act: 3.5799. Min Act: -0.1700

Data Index: 657440 (C4 (Web Text))

Max Activating Token Index: 256

Text #15

Max Range: 3.7364. Min Range: -3.7364

Max Act: 3.6112. Min Act: -0.1700

Data Index: 57910 (C4 (Web Text))

Max Activating Token Index: 855

Text #16

Max Range: 3.7364. Min Range: -3.7364

Max Act: 3.6112. Min Act: -0.1700

Data Index: 470538 (C4 (Web Text))

Max Activating Token Index: 294

Text #17

Max Range: 3.7364. Min Range: -3.7364

Max Act: 3.5642. Min Act: -0.1700

Data Index: 84305 (C4 (Web Text))

Max Activating Token Index: 519

Text #18

Max Range: 3.7364. Min Range: -3.7364

Max Act: 3.5642. Min Act: -0.1700

Data Index: 522912 (C4 (Web Text))

Max Activating Token Index: 197

Text #19

Max Range: 3.7364. Min Range: -3.7364

Max Act: 3.5799. Min Act: -0.1700

Data Index: 63611 (C4 (Web Text))

Max Activating Token Index: 428