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

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

Neuron 1459 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: 3.7223. Min Range: -3.7223

Max Act: 3.7223. Min Act: -0.1700

Data Index: 133694 (C4 (Web Text))

Max Activating Token Index: 850

Text #1

Max Range: 3.7223. Min Range: -3.7223

Max Act: 3.7223. Min Act: -0.1700

Data Index: 562871 (C4 (Web Text))

Max Activating Token Index: 687

Text #2

Max Range: 3.7223. Min Range: -3.7223

Max Act: 3.6597. Min Act: -0.1700

Data Index: 364321 (C4 (Web Text))

Max Activating Token Index: 723

Text #3

Max Range: 3.7223. Min Range: -3.7223

Max Act: 3.5657. Min Act: -0.1700

Data Index: 453374 (C4 (Web Text))

Max Activating Token Index: 937

Text #4

Max Range: 3.7223. Min Range: -3.7223

Max Act: 3.5657. Min Act: -0.1700

Data Index: 659321 (C4 (Web Text))

Max Activating Token Index: 169

Text #5

Max Range: 3.7223. Min Range: -3.7223

Max Act: 3.5657. Min Act: -0.1700

Data Index: 1273883 (C4 (Web Text))

Max Activating Token Index: 460

Text #6

Max Range: 3.7223. Min Range: -3.7223

Max Act: 3.5657. Min Act: -0.1700

Data Index: 438504 (C4 (Web Text))

Max Activating Token Index: 850

Text #7

Max Range: 3.7223. Min Range: -3.7223

Max Act: 3.5344. Min Act: -0.1700

Data Index: 678246 (C4 (Web Text))

Max Activating Token Index: 638

Text #8

Max Range: 3.7223. Min Range: -3.7223

Max Act: 3.5657. Min Act: -0.1700

Data Index: 228748 (C4 (Web Text))

Max Activating Token Index: 892

Text #9

Max Range: 3.7223. Min Range: -3.7223

Max Act: 3.5971. Min Act: -0.1700

Data Index: 560981 (C4 (Web Text))

Max Activating Token Index: 844

Text #10

Max Range: 3.7223. Min Range: -3.7223

Max Act: 3.5971. Min Act: -0.1700

Data Index: 1184182 (C4 (Web Text))

Max Activating Token Index: 942

Text #11

Max Range: 3.7223. Min Range: -3.7223

Max Act: 3.5344. Min Act: -0.1700

Data Index: 596319 (C4 (Web Text))

Max Activating Token Index: 205

Text #12

Max Range: 3.7223. Min Range: -3.7223

Max Act: 3.5971. Min Act: -0.1700

Data Index: 566028 (C4 (Web Text))

Max Activating Token Index: 486

Text #13

Max Range: 3.7223. Min Range: -3.7223

Max Act: 3.5657. Min Act: -0.1700

Data Index: 582473 (C4 (Web Text))

Max Activating Token Index: 294

Text #14

Max Range: 3.7223. Min Range: -3.7223

Max Act: 3.5031. Min Act: -0.1700

Data Index: 342019 (C4 (Web Text))

Max Activating Token Index: 146

Text #15

Max Range: 3.7223. Min Range: -3.7223

Max Act: 3.4717. Min Act: -0.1700

Data Index: 544546 (C4 (Web Text))

Max Activating Token Index: 799

Text #16

Max Range: 3.7223. Min Range: -3.7223

Max Act: 3.5344. Min Act: -0.1700

Data Index: 156389 (C4 (Web Text))

Max Activating Token Index: 736

Text #17

Max Range: 3.7223. Min Range: -3.7223

Max Act: 3.4090. Min Act: -0.1700

Data Index: 1223034 (C4 (Web Text))

Max Activating Token Index: 368

Text #18

Max Range: 3.7223. Min Range: -3.7223

Max Act: 3.4717. Min Act: -0.1700

Data Index: 1038547 (C4 (Web Text))

Max Activating Token Index: 578

Text #19

Max Range: 3.7223. Min Range: -3.7223

Max Act: 3.4404. Min Act: -0.1700

Data Index: 749738 (C4 (Web Text))

Max Activating Token Index: 904