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

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

Neuron 513 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: 3.1757. Min Range: -3.1757

Max Act: 3.1757. Min Act: -0.1700

Data Index: 374099 (C4 (Web Text))

Max Activating Token Index: 166

Text #1

Max Range: 3.1757. Min Range: -3.1757

Max Act: 3.1600. Min Act: -0.1700

Data Index: 1094908 (C4 (Web Text))

Max Activating Token Index: 191

Text #2

Max Range: 3.1757. Min Range: -3.1757

Max Act: 3.1285. Min Act: -0.1700

Data Index: 452478 (C4 (Web Text))

Max Activating Token Index: 392

Text #3

Max Range: 3.1757. Min Range: -3.1757

Max Act: 3.1442. Min Act: -0.1700

Data Index: 1192846 (C4 (Web Text))

Max Activating Token Index: 470

Text #4

Max Range: 3.1757. Min Range: -3.1757

Max Act: 3.1442. Min Act: -0.1700

Data Index: 170428 (C4 (Web Text))

Max Activating Token Index: 591

Text #5

Max Range: 3.1757. Min Range: -3.1757

Max Act: 3.1285. Min Act: -0.1700

Data Index: 1325616 (C4 (Web Text))

Max Activating Token Index: 503

Text #6

Max Range: 3.1757. Min Range: -3.1757

Max Act: 3.1285. Min Act: -0.1700

Data Index: 1244964 (C4 (Web Text))

Max Activating Token Index: 663

Text #7

Max Range: 3.1757. Min Range: -3.1757

Max Act: 3.0969. Min Act: -0.1700

Data Index: 1189433 (C4 (Web Text))

Max Activating Token Index: 85

Text #8

Max Range: 3.1757. Min Range: -3.1757

Max Act: 3.1127. Min Act: -0.1700

Data Index: 1151523 (C4 (Web Text))

Max Activating Token Index: 159

Text #9

Max Range: 3.1757. Min Range: -3.1757

Max Act: 3.0654. Min Act: -0.1700

Data Index: 813793 (C4 (Web Text))

Max Activating Token Index: 687

Text #10

Max Range: 3.1757. Min Range: -3.1757

Max Act: 3.0496. Min Act: -0.1700

Data Index: 1070602 (C4 (Web Text))

Max Activating Token Index: 454

Text #11

Max Range: 3.1757. Min Range: -3.1757

Max Act: 3.0338. Min Act: -0.1700

Data Index: 415837 (C4 (Web Text))

Max Activating Token Index: 493

Text #12

Max Range: 3.1757. Min Range: -3.1757

Max Act: 3.0180. Min Act: -0.1700

Data Index: 796478 (C4 (Web Text))

Max Activating Token Index: 448

Text #13

Max Range: 3.1757. Min Range: -3.1757

Max Act: 3.0022. Min Act: -0.1700

Data Index: 940455 (C4 (Web Text))

Max Activating Token Index: 805

Text #14

Max Range: 3.1757. Min Range: -3.1757

Max Act: 3.0654. Min Act: -0.1700

Data Index: 206082 (C4 (Web Text))

Max Activating Token Index: 115

Text #15

Max Range: 3.1757. Min Range: -3.1757

Max Act: 3.0496. Min Act: -0.1700

Data Index: 1299421 (C4 (Web Text))

Max Activating Token Index: 69

Text #16

Max Range: 3.1757. Min Range: -3.1757

Max Act: 3.0022. Min Act: -0.1700

Data Index: 30916 (C4 (Web Text))

Max Activating Token Index: 29

Text #17

Max Range: 3.1757. Min Range: -3.1757

Max Act: 3.0180. Min Act: -0.1700

Data Index: 796958 (C4 (Web Text))

Max Activating Token Index: 577

Text #18

Max Range: 3.1757. Min Range: -3.1757

Max Act: 3.0022. Min Act: -0.1700

Data Index: 778148 (C4 (Web Text))

Max Activating Token Index: 664

Text #19

Max Range: 3.1757. Min Range: -3.1757

Max Act: 3.0180. Min Act: -0.1700

Data Index: 793131 (C4 (Web Text))

Max Activating Token Index: 269