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

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

Neuron 1359 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: 6.1421. Min Range: -6.1421

Max Act: 6.1421. Min Act: -0.1700

Data Index: 82698 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 6.1421. Min Range: -6.1421

Max Act: 6.0796. Min Act: -0.1700

Data Index: 978157 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 6.1421. Min Range: -6.1421

Max Act: 6.0483. Min Act: -0.1700

Data Index: 827975 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 6.1421. Min Range: -6.1421

Max Act: 6.1421. Min Act: -0.1700

Data Index: 1216848 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 6.1421. Min Range: -6.1421

Max Act: 5.9233. Min Act: -0.1700

Data Index: 378065 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 6.1421. Min Range: -6.1421

Max Act: 5.9233. Min Act: -0.1700

Data Index: 1004838 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 6.1421. Min Range: -6.1421

Max Act: 5.7983. Min Act: -0.1700

Data Index: 1054 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 6.1421. Min Range: -6.1421

Max Act: 5.8608. Min Act: -0.1700

Data Index: 200775 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 6.1421. Min Range: -6.1421

Max Act: 5.8296. Min Act: -0.1700

Data Index: 261367 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 6.1421. Min Range: -6.1421

Max Act: 5.6733. Min Act: -0.1700

Data Index: 313787 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 6.1421. Min Range: -6.1421

Max Act: 5.7671. Min Act: -0.1700

Data Index: 920333 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 6.1421. Min Range: -6.1421

Max Act: 5.7671. Min Act: -0.1700

Data Index: 750599 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 6.1421. Min Range: -6.1421

Max Act: 5.6108. Min Act: -0.1700

Data Index: 1241374 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 6.1421. Min Range: -6.1421

Max Act: 5.7358. Min Act: -0.1700

Data Index: 1280792 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 6.1421. Min Range: -6.1421

Max Act: 5.5483. Min Act: -0.1700

Data Index: 886364 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 6.1421. Min Range: -6.1421

Max Act: 5.6108. Min Act: -0.1700

Data Index: 388161 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 6.1421. Min Range: -6.1421

Max Act: 5.6733. Min Act: -0.1700

Data Index: 1328511 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 6.1421. Min Range: -6.1421

Max Act: 5.6421. Min Act: -0.1700

Data Index: 1340811 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 6.1421. Min Range: -6.1421

Max Act: 5.6108. Min Act: -0.1700

Data Index: 221673 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 6.1421. Min Range: -6.1421

Max Act: 5.6421. Min Act: -0.1700

Data Index: 332562 (C4 (Web Text))

Max Activating Token Index: 1023