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

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

Neuron 2016 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0955. Min Range: -3.0955

Max Act: 3.0955. Min Act: -0.1700

Data Index: 1351432 (C4 (Web Text))

Max Activating Token Index: 224

Text #1

Max Range: 3.0955. Min Range: -3.0955

Max Act: 3.0166. Min Act: -0.1700

Data Index: 991846 (C4 (Web Text))

Max Activating Token Index: 790

Text #2

Max Range: 3.0955. Min Range: -3.0955

Max Act: 3.0324. Min Act: -0.1700

Data Index: 982252 (C4 (Web Text))

Max Activating Token Index: 580

Text #3

Max Range: 3.0955. Min Range: -3.0955

Max Act: 2.9691. Min Act: -0.1700

Data Index: 618929 (C4 (Web Text))

Max Activating Token Index: 921

Text #4

Max Range: 3.0955. Min Range: -3.0955

Max Act: 2.9375. Min Act: -0.1700

Data Index: 409437 (C4 (Web Text))

Max Activating Token Index: 503

Text #5

Max Range: 3.0955. Min Range: -3.0955

Max Act: 2.9691. Min Act: -0.1700

Data Index: 273186 (C4 (Web Text))

Max Activating Token Index: 445

Text #6

Max Range: 3.0955. Min Range: -3.0955

Max Act: 2.9216. Min Act: -0.1700

Data Index: 115453 (C4 (Web Text))

Max Activating Token Index: 790

Text #7

Max Range: 3.0955. Min Range: -3.0955

Max Act: 2.9216. Min Act: -0.1700

Data Index: 563167 (C4 (Web Text))

Max Activating Token Index: 869

Text #8

Max Range: 3.0955. Min Range: -3.0955

Max Act: 2.8899. Min Act: -0.1700

Data Index: 496985 (C4 (Web Text))

Max Activating Token Index: 649

Text #9

Max Range: 3.0955. Min Range: -3.0955

Max Act: 2.8899. Min Act: -0.1700

Data Index: 1333736 (C4 (Web Text))

Max Activating Token Index: 500

Text #10

Max Range: 3.0955. Min Range: -3.0955

Max Act: 2.8740. Min Act: -0.1700

Data Index: 543851 (C4 (Web Text))

Max Activating Token Index: 833

Text #11

Max Range: 3.0955. Min Range: -3.0955

Max Act: 2.9058. Min Act: -0.1700

Data Index: 38413 (C4 (Web Text))

Max Activating Token Index: 369

Text #12

Max Range: 3.0955. Min Range: -3.0955

Max Act: 2.9058. Min Act: -0.1700

Data Index: 21280 (C4 (Web Text))

Max Activating Token Index: 629

Text #13

Max Range: 3.0955. Min Range: -3.0955

Max Act: 2.9058. Min Act: -0.1700

Data Index: 1132087 (C4 (Web Text))

Max Activating Token Index: 24

Text #14

Max Range: 3.0955. Min Range: -3.0955

Max Act: 2.8899. Min Act: -0.1700

Data Index: 1229804 (C4 (Web Text))

Max Activating Token Index: 195

Text #15

Max Range: 3.0955. Min Range: -3.0955

Max Act: 2.8899. Min Act: -0.1700

Data Index: 1254226 (C4 (Web Text))

Max Activating Token Index: 21

Text #16

Max Range: 3.0955. Min Range: -3.0955

Max Act: 2.9058. Min Act: -0.1700

Data Index: 346924 (C4 (Web Text))

Max Activating Token Index: 926

Text #17

Max Range: 3.0955. Min Range: -3.0955

Max Act: 2.8740. Min Act: -0.1700

Data Index: 522380 (C4 (Web Text))

Max Activating Token Index: 887

Text #18

Max Range: 3.0955. Min Range: -3.0955

Max Act: 2.8899. Min Act: -0.1700

Data Index: 573950 (C4 (Web Text))

Max Activating Token Index: 750

Text #19

Max Range: 3.0955. Min Range: -3.0955

Max Act: 2.8740. Min Act: -0.1700

Data Index: 649704 (C4 (Web Text))

Max Activating Token Index: 897