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

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

Neuron 720 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: 5.7722. Min Range: -5.7722

Max Act: 5.7722. Min Act: -0.1700

Data Index: 827975 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 5.7722. Min Range: -5.7722

Max Act: 5.4285. Min Act: -0.1700

Data Index: 8175 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 5.7722. Min Range: -5.7722

Max Act: 5.3347. Min Act: -0.1700

Data Index: 490731 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 5.7722. Min Range: -5.7722

Max Act: 5.0535. Min Act: -0.1700

Data Index: 635508 (C4 (Web Text))

Max Activating Token Index: 566

Text #4

Max Range: 5.7722. Min Range: -5.7722

Max Act: 4.9597. Min Act: -0.1700

Data Index: 1118752 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 5.7722. Min Range: -5.7722

Max Act: 5.0535. Min Act: -0.1700

Data Index: 127899 (C4 (Web Text))

Max Activating Token Index: 175

Text #6

Max Range: 5.7722. Min Range: -5.7722

Max Act: 5.0222. Min Act: -0.1700

Data Index: 1358974 (C4 (Web Text))

Max Activating Token Index: 613

Text #7

Max Range: 5.7722. Min Range: -5.7722

Max Act: 4.9910. Min Act: -0.1700

Data Index: 826725 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 5.7722. Min Range: -5.7722

Max Act: 4.8972. Min Act: -0.1700

Data Index: 1208970 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 5.7722. Min Range: -5.7722

Max Act: 4.8347. Min Act: -0.1700

Data Index: 57859 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 5.7722. Min Range: -5.7722

Max Act: 4.9597. Min Act: -0.1700

Data Index: 246805 (C4 (Web Text))

Max Activating Token Index: 275

Text #11

Max Range: 5.7722. Min Range: -5.7722

Max Act: 4.9910. Min Act: -0.1700

Data Index: 1056464 (C4 (Web Text))

Max Activating Token Index: 940

Text #12

Max Range: 5.7722. Min Range: -5.7722

Max Act: 4.9285. Min Act: -0.1700

Data Index: 987050 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 5.7722. Min Range: -5.7722

Max Act: 4.8660. Min Act: -0.1700

Data Index: 867967 (C4 (Web Text))

Max Activating Token Index: 1006

Text #14

Max Range: 5.7722. Min Range: -5.7722

Max Act: 4.8972. Min Act: -0.1700

Data Index: 149503 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 5.7722. Min Range: -5.7722

Max Act: 4.8035. Min Act: -0.1700

Data Index: 428648 (C4 (Web Text))

Max Activating Token Index: 931

Text #16

Max Range: 5.7722. Min Range: -5.7722

Max Act: 4.7410. Min Act: -0.1700

Data Index: 281198 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 5.7722. Min Range: -5.7722

Max Act: 4.8035. Min Act: -0.1700

Data Index: 281349 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 5.7722. Min Range: -5.7722

Max Act: 4.7097. Min Act: -0.1700

Data Index: 1156430 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 5.7722. Min Range: -5.7722

Max Act: 4.8035. Min Act: -0.1700

Data Index: 656001 (C4 (Web Text))

Max Activating Token Index: 711