Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1710 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 5.0073. Min Range: -5.0073

Max Act: 5.0073. Min Act: -0.1700

Data Index: 250498 (C4 (Web Text))

Max Activating Token Index: 892

Text #1

Max Range: 5.0073. Min Range: -5.0073

Max Act: 4.8823. Min Act: -0.1700

Data Index: 1026366 (C4 (Web Text))

Max Activating Token Index: 352

Text #2

Max Range: 5.0073. Min Range: -5.0073

Max Act: 4.8198. Min Act: -0.1700

Data Index: 93488 (C4 (Web Text))

Max Activating Token Index: 498

Text #3

Max Range: 5.0073. Min Range: -5.0073

Max Act: 4.8198. Min Act: -0.1700

Data Index: 1196709 (C4 (Web Text))

Max Activating Token Index: 914

Text #4

Max Range: 5.0073. Min Range: -5.0073

Max Act: 4.7573. Min Act: -0.1700

Data Index: 1354202 (C4 (Web Text))

Max Activating Token Index: 739

Text #5

Max Range: 5.0073. Min Range: -5.0073

Max Act: 4.7573. Min Act: -0.1700

Data Index: 1348700 (C4 (Web Text))

Max Activating Token Index: 24

Text #6

Max Range: 5.0073. Min Range: -5.0073

Max Act: 4.7261. Min Act: -0.1700

Data Index: 446959 (C4 (Web Text))

Max Activating Token Index: 870

Text #7

Max Range: 5.0073. Min Range: -5.0073

Max Act: 4.7261. Min Act: -0.1700

Data Index: 228600 (C4 (Web Text))

Max Activating Token Index: 955

Text #8

Max Range: 5.0073. Min Range: -5.0073

Max Act: 4.6011. Min Act: -0.1700

Data Index: 234832 (C4 (Web Text))

Max Activating Token Index: 219

Text #9

Max Range: 5.0073. Min Range: -5.0073

Max Act: 4.6011. Min Act: -0.1700

Data Index: 880243 (C4 (Web Text))

Max Activating Token Index: 869

Text #10

Max Range: 5.0073. Min Range: -5.0073

Max Act: 4.6011. Min Act: -0.1700

Data Index: 467994 (C4 (Web Text))

Max Activating Token Index: 168

Text #11

Max Range: 5.0073. Min Range: -5.0073

Max Act: 4.5698. Min Act: -0.1700

Data Index: 493614 (C4 (Web Text))

Max Activating Token Index: 671

Text #12

Max Range: 5.0073. Min Range: -5.0073

Max Act: 4.5698. Min Act: -0.1700

Data Index: 211313 (C4 (Web Text))

Max Activating Token Index: 951

Text #13

Max Range: 5.0073. Min Range: -5.0073

Max Act: 4.5386. Min Act: -0.1700

Data Index: 940560 (C4 (Web Text))

Max Activating Token Index: 638

Text #14

Max Range: 5.0073. Min Range: -5.0073

Max Act: 4.5386. Min Act: -0.1700

Data Index: 388585 (C4 (Web Text))

Max Activating Token Index: 417

Text #15

Max Range: 5.0073. Min Range: -5.0073

Max Act: 4.5386. Min Act: -0.1700

Data Index: 1068034 (C4 (Web Text))

Max Activating Token Index: 20

Text #16

Max Range: 5.0073. Min Range: -5.0073

Max Act: 4.5073. Min Act: -0.1700

Data Index: 545079 (C4 (Web Text))

Max Activating Token Index: 368

Text #17

Max Range: 5.0073. Min Range: -5.0073

Max Act: 4.5698. Min Act: -0.1700

Data Index: 1203429 (C4 (Web Text))

Max Activating Token Index: 19

Text #18

Max Range: 5.0073. Min Range: -5.0073

Max Act: 4.5386. Min Act: -0.1700

Data Index: 1263079 (C4 (Web Text))

Max Activating Token Index: 388

Text #19

Max Range: 5.0073. Min Range: -5.0073

Max Act: 4.4761. Min Act: -0.1700

Data Index: 1286397 (C4 (Web Text))

Max Activating Token Index: 124