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

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

Neuron 1802 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: 3.5878. Min Range: -3.5878

Max Act: 3.5878. Min Act: -0.1700

Data Index: 751567 (C4 (Web Text))

Max Activating Token Index: 986

Text #1

Max Range: 3.5878. Min Range: -3.5878

Max Act: 3.5565. Min Act: -0.1700

Data Index: 201444 (C4 (Web Text))

Max Activating Token Index: 693

Text #2

Max Range: 3.5878. Min Range: -3.5878

Max Act: 3.5565. Min Act: -0.1700

Data Index: 175606 (C4 (Web Text))

Max Activating Token Index: 644

Text #3

Max Range: 3.5878. Min Range: -3.5878

Max Act: 3.5565. Min Act: -0.1700

Data Index: 668904 (C4 (Web Text))

Max Activating Token Index: 121

Text #4

Max Range: 3.5878. Min Range: -3.5878

Max Act: 3.5565. Min Act: -0.1700

Data Index: 296441 (C4 (Web Text))

Max Activating Token Index: 256

Text #5

Max Range: 3.5878. Min Range: -3.5878

Max Act: 3.5252. Min Act: -0.1700

Data Index: 1134546 (C4 (Web Text))

Max Activating Token Index: 936

Text #6

Max Range: 3.5878. Min Range: -3.5878

Max Act: 3.5252. Min Act: -0.1700

Data Index: 904453 (C4 (Web Text))

Max Activating Token Index: 700

Text #7

Max Range: 3.5878. Min Range: -3.5878

Max Act: 3.5252. Min Act: -0.1700

Data Index: 903717 (C4 (Web Text))

Max Activating Token Index: 694

Text #8

Max Range: 3.5878. Min Range: -3.5878

Max Act: 3.4938. Min Act: -0.1700

Data Index: 732948 (C4 (Web Text))

Max Activating Token Index: 558

Text #9

Max Range: 3.5878. Min Range: -3.5878

Max Act: 3.5252. Min Act: -0.1700

Data Index: 354209 (C4 (Web Text))

Max Activating Token Index: 882

Text #10

Max Range: 3.5878. Min Range: -3.5878

Max Act: 3.4938. Min Act: -0.1700

Data Index: 672920 (C4 (Web Text))

Max Activating Token Index: 317

Text #11

Max Range: 3.5878. Min Range: -3.5878

Max Act: 3.4938. Min Act: -0.1700

Data Index: 1223693 (C4 (Web Text))

Max Activating Token Index: 770

Text #12

Max Range: 3.5878. Min Range: -3.5878

Max Act: 3.5252. Min Act: -0.1700

Data Index: 1112279 (C4 (Web Text))

Max Activating Token Index: 472

Text #13

Max Range: 3.5878. Min Range: -3.5878

Max Act: 3.4938. Min Act: -0.1700

Data Index: 323875 (C4 (Web Text))

Max Activating Token Index: 368

Text #14

Max Range: 3.5878. Min Range: -3.5878

Max Act: 3.4938. Min Act: -0.1700

Data Index: 307251 (C4 (Web Text))

Max Activating Token Index: 909

Text #15

Max Range: 3.5878. Min Range: -3.5878

Max Act: 3.4938. Min Act: -0.1700

Data Index: 542817 (C4 (Web Text))

Max Activating Token Index: 775

Text #16

Max Range: 3.5878. Min Range: -3.5878

Max Act: 3.4311. Min Act: -0.1700

Data Index: 623385 (C4 (Web Text))

Max Activating Token Index: 553

Text #17

Max Range: 3.5878. Min Range: -3.5878

Max Act: 3.4938. Min Act: -0.1700

Data Index: 618373 (C4 (Web Text))

Max Activating Token Index: 874

Text #18

Max Range: 3.5878. Min Range: -3.5878

Max Act: 3.4625. Min Act: -0.1700

Data Index: 1009557 (C4 (Web Text))

Max Activating Token Index: 37

Text #19

Max Range: 3.5878. Min Range: -3.5878

Max Act: 3.4625. Min Act: -0.1700

Data Index: 464639 (C4 (Web Text))

Max Activating Token Index: 342