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

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

Neuron 1413 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: 3.9049. Min Range: -3.9049

Max Act: 3.9049. Min Act: -0.1700

Data Index: 843133 (C4 (Web Text))

Max Activating Token Index: 624

Text #1

Max Range: 3.9049. Min Range: -3.9049

Max Act: 3.8111. Min Act: -0.1700

Data Index: 19880 (C4 (Web Text))

Max Activating Token Index: 61

Text #2

Max Range: 3.9049. Min Range: -3.9049

Max Act: 3.7641. Min Act: -0.1700

Data Index: 457519 (C4 (Web Text))

Max Activating Token Index: 688

Text #3

Max Range: 3.9049. Min Range: -3.9049

Max Act: 3.7798. Min Act: -0.1700

Data Index: 1304017 (C4 (Web Text))

Max Activating Token Index: 46

Text #4

Max Range: 3.9049. Min Range: -3.9049

Max Act: 3.7798. Min Act: -0.1700

Data Index: 185634 (C4 (Web Text))

Max Activating Token Index: 8

Text #5

Max Range: 3.9049. Min Range: -3.9049

Max Act: 3.7641. Min Act: -0.1700

Data Index: 1036018 (C4 (Web Text))

Max Activating Token Index: 216

Text #6

Max Range: 3.9049. Min Range: -3.9049

Max Act: 3.7485. Min Act: -0.1700

Data Index: 1241537 (C4 (Web Text))

Max Activating Token Index: 863

Text #7

Max Range: 3.9049. Min Range: -3.9049

Max Act: 3.7328. Min Act: -0.1700

Data Index: 912741 (C4 (Web Text))

Max Activating Token Index: 155

Text #8

Max Range: 3.9049. Min Range: -3.9049

Max Act: 3.7328. Min Act: -0.1700

Data Index: 664483 (C4 (Web Text))

Max Activating Token Index: 642

Text #9

Max Range: 3.9049. Min Range: -3.9049

Max Act: 3.7485. Min Act: -0.1700

Data Index: 209166 (C4 (Web Text))

Max Activating Token Index: 930

Text #10

Max Range: 3.9049. Min Range: -3.9049

Max Act: 3.7485. Min Act: -0.1700

Data Index: 981273 (C4 (Web Text))

Max Activating Token Index: 983

Text #11

Max Range: 3.9049. Min Range: -3.9049

Max Act: 3.7485. Min Act: -0.1700

Data Index: 745269 (C4 (Web Text))

Max Activating Token Index: 804

Text #12

Max Range: 3.9049. Min Range: -3.9049

Max Act: 3.7328. Min Act: -0.1700

Data Index: 606410 (C4 (Web Text))

Max Activating Token Index: 800

Text #13

Max Range: 3.9049. Min Range: -3.9049

Max Act: 3.7485. Min Act: -0.1700

Data Index: 664820 (C4 (Web Text))

Max Activating Token Index: 704

Text #14

Max Range: 3.9049. Min Range: -3.9049

Max Act: 3.7172. Min Act: -0.1700

Data Index: 673326 (C4 (Web Text))

Max Activating Token Index: 273

Text #15

Max Range: 3.9049. Min Range: -3.9049

Max Act: 3.7485. Min Act: -0.1700

Data Index: 457718 (C4 (Web Text))

Max Activating Token Index: 551

Text #16

Max Range: 3.9049. Min Range: -3.9049

Max Act: 3.7016. Min Act: -0.1700

Data Index: 727356 (C4 (Web Text))

Max Activating Token Index: 55

Text #17

Max Range: 3.9049. Min Range: -3.9049

Max Act: 3.7172. Min Act: -0.1700

Data Index: 294467 (C4 (Web Text))

Max Activating Token Index: 743

Text #18

Max Range: 3.9049. Min Range: -3.9049

Max Act: 3.7172. Min Act: -0.1700

Data Index: 836880 (C4 (Web Text))

Max Activating Token Index: 914

Text #19

Max Range: 3.9049. Min Range: -3.9049

Max Act: 3.7016. Min Act: -0.1700

Data Index: 635592 (C4 (Web Text))

Max Activating Token Index: 570