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

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

Neuron 594 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.5035. Min Range: -5.5035

Max Act: 5.5035. Min Act: -0.1700

Data Index: 1042956 (C4 (Web Text))

Max Activating Token Index: 142

Text #1

Max Range: 5.5035. Min Range: -5.5035

Max Act: 5.3160. Min Act: -0.1700

Data Index: 1279750 (C4 (Web Text))

Max Activating Token Index: 879

Text #2

Max Range: 5.5035. Min Range: -5.5035

Max Act: 5.1910. Min Act: -0.1700

Data Index: 534886 (C4 (Web Text))

Max Activating Token Index: 760

Text #3

Max Range: 5.5035. Min Range: -5.5035

Max Act: 5.0660. Min Act: -0.1700

Data Index: 535506 (C4 (Web Text))

Max Activating Token Index: 388

Text #4

Max Range: 5.5035. Min Range: -5.5035

Max Act: 5.1285. Min Act: -0.1700

Data Index: 545671 (C4 (Web Text))

Max Activating Token Index: 783

Text #5

Max Range: 5.5035. Min Range: -5.5035

Max Act: 5.0660. Min Act: -0.1700

Data Index: 942624 (C4 (Web Text))

Max Activating Token Index: 686

Text #6

Max Range: 5.5035. Min Range: -5.5035

Max Act: 5.0660. Min Act: -0.1700

Data Index: 612263 (C4 (Web Text))

Max Activating Token Index: 197

Text #7

Max Range: 5.5035. Min Range: -5.5035

Max Act: 5.0348. Min Act: -0.1700

Data Index: 755065 (C4 (Web Text))

Max Activating Token Index: 26

Text #8

Max Range: 5.5035. Min Range: -5.5035

Max Act: 5.0348. Min Act: -0.1700

Data Index: 1025653 (C4 (Web Text))

Max Activating Token Index: 398

Text #9

Max Range: 5.5035. Min Range: -5.5035

Max Act: 5.0348. Min Act: -0.1700

Data Index: 760470 (C4 (Web Text))

Max Activating Token Index: 760

Text #10

Max Range: 5.5035. Min Range: -5.5035

Max Act: 5.0035. Min Act: -0.1700

Data Index: 364673 (C4 (Web Text))

Max Activating Token Index: 55

Text #11

Max Range: 5.5035. Min Range: -5.5035

Max Act: 5.0035. Min Act: -0.1700

Data Index: 391794 (C4 (Web Text))

Max Activating Token Index: 12

Text #12

Max Range: 5.5035. Min Range: -5.5035

Max Act: 5.0348. Min Act: -0.1700

Data Index: 738245 (C4 (Web Text))

Max Activating Token Index: 294

Text #13

Max Range: 5.5035. Min Range: -5.5035

Max Act: 4.9723. Min Act: -0.1700

Data Index: 644053 (C4 (Web Text))

Max Activating Token Index: 526

Text #14

Max Range: 5.5035. Min Range: -5.5035

Max Act: 4.9410. Min Act: -0.1700

Data Index: 356340 (C4 (Web Text))

Max Activating Token Index: 178

Text #15

Max Range: 5.5035. Min Range: -5.5035

Max Act: 5.0035. Min Act: -0.1700

Data Index: 283270 (C4 (Web Text))

Max Activating Token Index: 995

Text #16

Max Range: 5.5035. Min Range: -5.5035

Max Act: 5.0348. Min Act: -0.1700

Data Index: 337289 (C4 (Web Text))

Max Activating Token Index: 556

Text #17

Max Range: 5.5035. Min Range: -5.5035

Max Act: 4.9410. Min Act: -0.1700

Data Index: 735524 (C4 (Web Text))

Max Activating Token Index: 408

Text #18

Max Range: 5.5035. Min Range: -5.5035

Max Act: 4.9410. Min Act: -0.1700

Data Index: 897585 (C4 (Web Text))

Max Activating Token Index: 406

Text #19

Max Range: 5.5035. Min Range: -5.5035

Max Act: 4.9723. Min Act: -0.1700

Data Index: 111565 (C4 (Web Text))

Max Activating Token Index: 728