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

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

Neuron 381 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5825. Min Range: -3.5825

Max Act: 3.5825. Min Act: -0.1700

Data Index: 998116 (C4 (Web Text))

Max Activating Token Index: 10

Text #1

Max Range: 3.5825. Min Range: -3.5825

Max Act: 3.5199. Min Act: -0.1700

Data Index: 878153 (C4 (Web Text))

Max Activating Token Index: 57

Text #2

Max Range: 3.5825. Min Range: -3.5825

Max Act: 3.5355. Min Act: -0.1700

Data Index: 1351780 (C4 (Web Text))

Max Activating Token Index: 114

Text #3

Max Range: 3.5825. Min Range: -3.5825

Max Act: 3.5199. Min Act: -0.1700

Data Index: 593652 (C4 (Web Text))

Max Activating Token Index: 10

Text #4

Max Range: 3.5825. Min Range: -3.5825

Max Act: 3.5042. Min Act: -0.1700

Data Index: 121416 (C4 (Web Text))

Max Activating Token Index: 865

Text #5

Max Range: 3.5825. Min Range: -3.5825

Max Act: 3.4885. Min Act: -0.1700

Data Index: 19379 (C4 (Web Text))

Max Activating Token Index: 3

Text #6

Max Range: 3.5825. Min Range: -3.5825

Max Act: 3.4728. Min Act: -0.1700

Data Index: 1248272 (C4 (Web Text))

Max Activating Token Index: 88

Text #7

Max Range: 3.5825. Min Range: -3.5825

Max Act: 3.4572. Min Act: -0.1700

Data Index: 406165 (C4 (Web Text))

Max Activating Token Index: 31

Text #8

Max Range: 3.5825. Min Range: -3.5825

Max Act: 3.4415. Min Act: -0.1700

Data Index: 710693 (C4 (Web Text))

Max Activating Token Index: 52

Text #9

Max Range: 3.5825. Min Range: -3.5825

Max Act: 3.4415. Min Act: -0.1700

Data Index: 814119 (C4 (Web Text))

Max Activating Token Index: 11

Text #10

Max Range: 3.5825. Min Range: -3.5825

Max Act: 3.4258. Min Act: -0.1700

Data Index: 912729 (C4 (Web Text))

Max Activating Token Index: 838

Text #11

Max Range: 3.5825. Min Range: -3.5825

Max Act: 3.4415. Min Act: -0.1700

Data Index: 277080 (C4 (Web Text))

Max Activating Token Index: 18

Text #12

Max Range: 3.5825. Min Range: -3.5825

Max Act: 3.4415. Min Act: -0.1700

Data Index: 130714 (C4 (Web Text))

Max Activating Token Index: 221

Text #13

Max Range: 3.5825. Min Range: -3.5825

Max Act: 3.4415. Min Act: -0.1700

Data Index: 768519 (C4 (Web Text))

Max Activating Token Index: 357

Text #14

Max Range: 3.5825. Min Range: -3.5825

Max Act: 3.4101. Min Act: -0.1700

Data Index: 519723 (C4 (Web Text))

Max Activating Token Index: 893

Text #15

Max Range: 3.5825. Min Range: -3.5825

Max Act: 3.4258. Min Act: -0.1700

Data Index: 154198 (C4 (Web Text))

Max Activating Token Index: 109

Text #16

Max Range: 3.5825. Min Range: -3.5825

Max Act: 3.4258. Min Act: -0.1700

Data Index: 1240420 (C4 (Web Text))

Max Activating Token Index: 827

Text #17

Max Range: 3.5825. Min Range: -3.5825

Max Act: 3.4101. Min Act: -0.1700

Data Index: 590538 (C4 (Web Text))

Max Activating Token Index: 789

Text #18

Max Range: 3.5825. Min Range: -3.5825

Max Act: 3.4258. Min Act: -0.1700

Data Index: 832018 (C4 (Web Text))

Max Activating Token Index: 936

Text #19

Max Range: 3.5825. Min Range: -3.5825

Max Act: 3.4101. Min Act: -0.1700

Data Index: 1007261 (C4 (Web Text))

Max Activating Token Index: 312