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

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

Neuron 954 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 8.1121. Min Range: -8.1121

Max Act: 8.1121. Min Act: -0.1700

Data Index: 368020 (C4 (Web Text))

Max Activating Token Index: 628

Text #1

Max Range: 8.1121. Min Range: -8.1121

Max Act: 7.9558. Min Act: -0.1700

Data Index: 703654 (C4 (Web Text))

Max Activating Token Index: 1022

Text #2

Max Range: 8.1121. Min Range: -8.1121

Max Act: 7.9558. Min Act: -0.1700

Data Index: 362850 (C4 (Web Text))

Max Activating Token Index: 161

Text #3

Max Range: 8.1121. Min Range: -8.1121

Max Act: 8.0183. Min Act: -0.1700

Data Index: 926631 (C4 (Web Text))

Max Activating Token Index: 728

Text #4

Max Range: 8.1121. Min Range: -8.1121

Max Act: 7.9246. Min Act: -0.1700

Data Index: 1156097 (C4 (Web Text))

Max Activating Token Index: 305

Text #5

Max Range: 8.1121. Min Range: -8.1121

Max Act: 7.9871. Min Act: -0.1700

Data Index: 525450 (C4 (Web Text))

Max Activating Token Index: 138

Text #6

Max Range: 8.1121. Min Range: -8.1121

Max Act: 7.8308. Min Act: -0.1700

Data Index: 844133 (C4 (Web Text))

Max Activating Token Index: 978

Text #7

Max Range: 8.1121. Min Range: -8.1121

Max Act: 7.8933. Min Act: -0.1700

Data Index: 236287 (C4 (Web Text))

Max Activating Token Index: 990

Text #8

Max Range: 8.1121. Min Range: -8.1121

Max Act: 7.8933. Min Act: -0.1700

Data Index: 1058854 (C4 (Web Text))

Max Activating Token Index: 827

Text #9

Max Range: 8.1121. Min Range: -8.1121

Max Act: 7.9246. Min Act: -0.1700

Data Index: 479915 (C4 (Web Text))

Max Activating Token Index: 1009

Text #10

Max Range: 8.1121. Min Range: -8.1121

Max Act: 7.8308. Min Act: -0.1700

Data Index: 871065 (C4 (Web Text))

Max Activating Token Index: 956

Text #11

Max Range: 8.1121. Min Range: -8.1121

Max Act: 7.8933. Min Act: -0.1700

Data Index: 350785 (C4 (Web Text))

Max Activating Token Index: 452

Text #12

Max Range: 8.1121. Min Range: -8.1121

Max Act: 7.7996. Min Act: -0.1700

Data Index: 443670 (C4 (Web Text))

Max Activating Token Index: 967

Text #13

Max Range: 8.1121. Min Range: -8.1121

Max Act: 7.8933. Min Act: -0.1700

Data Index: 154158 (C4 (Web Text))

Max Activating Token Index: 141

Text #14

Max Range: 8.1121. Min Range: -8.1121

Max Act: 7.8621. Min Act: -0.1700

Data Index: 1357005 (C4 (Web Text))

Max Activating Token Index: 533

Text #15

Max Range: 8.1121. Min Range: -8.1121

Max Act: 7.7058. Min Act: -0.1700

Data Index: 350627 (C4 (Web Text))

Max Activating Token Index: 809

Text #16

Max Range: 8.1121. Min Range: -8.1121

Max Act: 7.8621. Min Act: -0.1700

Data Index: 120797 (C4 (Web Text))

Max Activating Token Index: 224

Text #17

Max Range: 8.1121. Min Range: -8.1121

Max Act: 7.8308. Min Act: -0.1700

Data Index: 44797 (C4 (Web Text))

Max Activating Token Index: 816

Text #18

Max Range: 8.1121. Min Range: -8.1121

Max Act: 7.7996. Min Act: -0.1700

Data Index: 452925 (C4 (Web Text))

Max Activating Token Index: 694

Text #19

Max Range: 8.1121. Min Range: -8.1121

Max Act: 7.8621. Min Act: -0.1700

Data Index: 741924 (C4 (Web Text))

Max Activating Token Index: 939