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

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

Neuron 1988 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.8871. Min Range: -3.8871

Max Act: 3.8871. Min Act: -0.1700

Data Index: 1087381 (C4 (Web Text))

Max Activating Token Index: 205

Text #1

Max Range: 3.8871. Min Range: -3.8871

Max Act: 3.8558. Min Act: -0.1700

Data Index: 1226689 (C4 (Web Text))

Max Activating Token Index: 261

Text #2

Max Range: 3.8871. Min Range: -3.8871

Max Act: 3.8558. Min Act: -0.1700

Data Index: 527327 (C4 (Web Text))

Max Activating Token Index: 790

Text #3

Max Range: 3.8871. Min Range: -3.8871

Max Act: 3.8871. Min Act: -0.1700

Data Index: 170855 (C4 (Web Text))

Max Activating Token Index: 907

Text #4

Max Range: 3.8871. Min Range: -3.8871

Max Act: 3.8558. Min Act: -0.1700

Data Index: 355026 (C4 (Web Text))

Max Activating Token Index: 96

Text #5

Max Range: 3.8871. Min Range: -3.8871

Max Act: 3.8558. Min Act: -0.1700

Data Index: 1016204 (C4 (Web Text))

Max Activating Token Index: 285

Text #6

Max Range: 3.8871. Min Range: -3.8871

Max Act: 3.7932. Min Act: -0.1700

Data Index: 789897 (C4 (Web Text))

Max Activating Token Index: 37

Text #7

Max Range: 3.8871. Min Range: -3.8871

Max Act: 3.8245. Min Act: -0.1700

Data Index: 265114 (C4 (Web Text))

Max Activating Token Index: 302

Text #8

Max Range: 3.8871. Min Range: -3.8871

Max Act: 3.7932. Min Act: -0.1700

Data Index: 698136 (C4 (Web Text))

Max Activating Token Index: 127

Text #9

Max Range: 3.8871. Min Range: -3.8871

Max Act: 3.7619. Min Act: -0.1700

Data Index: 1081331 (C4 (Web Text))

Max Activating Token Index: 109

Text #10

Max Range: 3.8871. Min Range: -3.8871

Max Act: 3.8245. Min Act: -0.1700

Data Index: 516541 (C4 (Web Text))

Max Activating Token Index: 968

Text #11

Max Range: 3.8871. Min Range: -3.8871

Max Act: 3.7307. Min Act: -0.1700

Data Index: 525147 (C4 (Web Text))

Max Activating Token Index: 890

Text #12

Max Range: 3.8871. Min Range: -3.8871

Max Act: 3.7619. Min Act: -0.1700

Data Index: 241929 (C4 (Web Text))

Max Activating Token Index: 551

Text #13

Max Range: 3.8871. Min Range: -3.8871

Max Act: 3.7619. Min Act: -0.1700

Data Index: 1289821 (C4 (Web Text))

Max Activating Token Index: 945

Text #14

Max Range: 3.8871. Min Range: -3.8871

Max Act: 3.7307. Min Act: -0.1700

Data Index: 254742 (C4 (Web Text))

Max Activating Token Index: 102

Text #15

Max Range: 3.8871. Min Range: -3.8871

Max Act: 3.7307. Min Act: -0.1700

Data Index: 85005 (C4 (Web Text))

Max Activating Token Index: 854

Text #16

Max Range: 3.8871. Min Range: -3.8871

Max Act: 3.7307. Min Act: -0.1700

Data Index: 390388 (C4 (Web Text))

Max Activating Token Index: 653

Text #17

Max Range: 3.8871. Min Range: -3.8871

Max Act: 3.6994. Min Act: -0.1700

Data Index: 901495 (C4 (Web Text))

Max Activating Token Index: 125

Text #18

Max Range: 3.8871. Min Range: -3.8871

Max Act: 3.6837. Min Act: -0.1700

Data Index: 1088619 (C4 (Web Text))

Max Activating Token Index: 954

Text #19

Max Range: 3.8871. Min Range: -3.8871

Max Act: 3.6524. Min Act: -0.1700

Data Index: 101346 (C4 (Web Text))

Max Activating Token Index: 604