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

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

Neuron 1202 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: 4.0753. Min Range: -4.0753

Max Act: 4.0753. Min Act: -0.1700

Data Index: 1263004 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 4.0753. Min Range: -4.0753

Max Act: 3.9502. Min Act: -0.1700

Data Index: 672876 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 4.0753. Min Range: -4.0753

Max Act: 3.8877. Min Act: -0.1700

Data Index: 1087546 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 4.0753. Min Range: -4.0753

Max Act: 3.9190. Min Act: -0.1700

Data Index: 466373 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 4.0753. Min Range: -4.0753

Max Act: 3.8564. Min Act: -0.1700

Data Index: 436325 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 4.0753. Min Range: -4.0753

Max Act: 3.8251. Min Act: -0.1700

Data Index: 547296 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 4.0753. Min Range: -4.0753

Max Act: 3.8251. Min Act: -0.1700

Data Index: 765698 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 4.0753. Min Range: -4.0753

Max Act: 3.7000. Min Act: -0.1700

Data Index: 911892 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 4.0753. Min Range: -4.0753

Max Act: 3.7000. Min Act: -0.1700

Data Index: 328794 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 4.0753. Min Range: -4.0753

Max Act: 3.7000. Min Act: -0.1700

Data Index: 109133 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 4.0753. Min Range: -4.0753

Max Act: 3.6061. Min Act: -0.1700

Data Index: 728423 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 4.0753. Min Range: -4.0753

Max Act: 3.6374. Min Act: -0.1700

Data Index: 215412 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 4.0753. Min Range: -4.0753

Max Act: 3.6061. Min Act: -0.1700

Data Index: 965496 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 4.0753. Min Range: -4.0753

Max Act: 3.6061. Min Act: -0.1700

Data Index: 66135 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 4.0753. Min Range: -4.0753

Max Act: 3.6374. Min Act: -0.1700

Data Index: 155672 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 4.0753. Min Range: -4.0753

Max Act: 3.5748. Min Act: -0.1700

Data Index: 482349 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 4.0753. Min Range: -4.0753

Max Act: 3.5748. Min Act: -0.1700

Data Index: 1347509 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 4.0753. Min Range: -4.0753

Max Act: 3.5748. Min Act: -0.1700

Data Index: 158163 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 4.0753. Min Range: -4.0753

Max Act: 3.5748. Min Act: -0.1700

Data Index: 617179 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 4.0753. Min Range: -4.0753

Max Act: 3.5748. Min Act: -0.1700

Data Index: 481256 (C4 (Web Text))

Max Activating Token Index: 1023