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

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

Neuron 737 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: 3.8305. Min Range: -3.8305

Max Act: 3.8305. Min Act: -0.1700

Data Index: 378778 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 3.8305. Min Range: -3.8305

Max Act: 3.8305. Min Act: -0.1700

Data Index: 763595 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 3.8305. Min Range: -3.8305

Max Act: 3.8305. Min Act: -0.1700

Data Index: 90853 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 3.8305. Min Range: -3.8305

Max Act: 3.7366. Min Act: -0.1700

Data Index: 216633 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 3.8305. Min Range: -3.8305

Max Act: 3.7053. Min Act: -0.1700

Data Index: 353879 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 3.8305. Min Range: -3.8305

Max Act: 3.6740. Min Act: -0.1700

Data Index: 440257 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 3.8305. Min Range: -3.8305

Max Act: 3.6427. Min Act: -0.1700

Data Index: 992373 (C4 (Web Text))

Max Activating Token Index: 422

Text #7

Max Range: 3.8305. Min Range: -3.8305

Max Act: 3.6114. Min Act: -0.1700

Data Index: 247566 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 3.8305. Min Range: -3.8305

Max Act: 3.6114. Min Act: -0.1700

Data Index: 1095238 (C4 (Web Text))

Max Activating Token Index: 920

Text #9

Max Range: 3.8305. Min Range: -3.8305

Max Act: 3.5488. Min Act: -0.1700

Data Index: 1086990 (C4 (Web Text))

Max Activating Token Index: 192

Text #10

Max Range: 3.8305. Min Range: -3.8305

Max Act: 3.5801. Min Act: -0.1700

Data Index: 593948 (C4 (Web Text))

Max Activating Token Index: 764

Text #11

Max Range: 3.8305. Min Range: -3.8305

Max Act: 3.5801. Min Act: -0.1700

Data Index: 759594 (C4 (Web Text))

Max Activating Token Index: 939

Text #12

Max Range: 3.8305. Min Range: -3.8305

Max Act: 3.5488. Min Act: -0.1700

Data Index: 37791 (C4 (Web Text))

Max Activating Token Index: 430

Text #13

Max Range: 3.8305. Min Range: -3.8305

Max Act: 3.5488. Min Act: -0.1700

Data Index: 797751 (C4 (Web Text))

Max Activating Token Index: 704

Text #14

Max Range: 3.8305. Min Range: -3.8305

Max Act: 3.5801. Min Act: -0.1700

Data Index: 909966 (C4 (Web Text))

Max Activating Token Index: 744

Text #15

Max Range: 3.8305. Min Range: -3.8305

Max Act: 3.5801. Min Act: -0.1700

Data Index: 373511 (C4 (Web Text))

Max Activating Token Index: 690

Text #16

Max Range: 3.8305. Min Range: -3.8305

Max Act: 3.5488. Min Act: -0.1700

Data Index: 378926 (C4 (Web Text))

Max Activating Token Index: 460

Text #17

Max Range: 3.8305. Min Range: -3.8305

Max Act: 3.5801. Min Act: -0.1700

Data Index: 273424 (C4 (Web Text))

Max Activating Token Index: 505

Text #18

Max Range: 3.8305. Min Range: -3.8305

Max Act: 3.5801. Min Act: -0.1700

Data Index: 1168972 (C4 (Web Text))

Max Activating Token Index: 662

Text #19

Max Range: 3.8305. Min Range: -3.8305

Max Act: 3.5801. Min Act: -0.1700

Data Index: 372726 (C4 (Web Text))

Max Activating Token Index: 601