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

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

Neuron 475 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: 3.8938. Min Range: -3.8938

Max Act: 3.8938. Min Act: -0.1700

Data Index: 263550 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 3.8938. Min Range: -3.8938

Max Act: 3.8625. Min Act: -0.1700

Data Index: 414942 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 3.8938. Min Range: -3.8938

Max Act: 3.8625. Min Act: -0.1700

Data Index: 1045768 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 3.8938. Min Range: -3.8938

Max Act: 3.8625. Min Act: -0.1700

Data Index: 908018 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 3.8938. Min Range: -3.8938

Max Act: 3.8625. Min Act: -0.1700

Data Index: 1297531 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 3.8938. Min Range: -3.8938

Max Act: 3.8000. Min Act: -0.1700

Data Index: 89658 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 3.8938. Min Range: -3.8938

Max Act: 3.8313. Min Act: -0.1700

Data Index: 91947 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 3.8938. Min Range: -3.8938

Max Act: 3.8625. Min Act: -0.1700

Data Index: 98246 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 3.8938. Min Range: -3.8938

Max Act: 3.8313. Min Act: -0.1700

Data Index: 22438 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 3.8938. Min Range: -3.8938

Max Act: 3.8000. Min Act: -0.1700

Data Index: 1000967 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 3.8938. Min Range: -3.8938

Max Act: 3.8000. Min Act: -0.1700

Data Index: 370609 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 3.8938. Min Range: -3.8938

Max Act: 3.8000. Min Act: -0.1700

Data Index: 733834 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 3.8938. Min Range: -3.8938

Max Act: 3.8000. Min Act: -0.1700

Data Index: 38818 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 3.8938. Min Range: -3.8938

Max Act: 3.8000. Min Act: -0.1700

Data Index: 216815 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 3.8938. Min Range: -3.8938

Max Act: 3.8000. Min Act: -0.1700

Data Index: 456194 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 3.8938. Min Range: -3.8938

Max Act: 3.7687. Min Act: -0.1700

Data Index: 989229 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 3.8938. Min Range: -3.8938

Max Act: 3.8000. Min Act: -0.1700

Data Index: 219089 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 3.8938. Min Range: -3.8938

Max Act: 3.8000. Min Act: -0.1700

Data Index: 643581 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 3.8938. Min Range: -3.8938

Max Act: 3.8000. Min Act: -0.1700

Data Index: 135429 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 3.8938. Min Range: -3.8938

Max Act: 3.8000. Min Act: -0.1700

Data Index: 1055480 (C4 (Web Text))

Max Activating Token Index: 1023