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

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

Neuron 59 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: 3.8478. Min Range: -3.8478

Max Act: 3.8478. Min Act: -0.1700

Data Index: 209103 (C4 (Web Text))

Max Activating Token Index: 319

Text #1

Max Range: 3.8478. Min Range: -3.8478

Max Act: 3.7852. Min Act: -0.1700

Data Index: 794296 (C4 (Web Text))

Max Activating Token Index: 738

Text #2

Max Range: 3.8478. Min Range: -3.8478

Max Act: 3.7852. Min Act: -0.1700

Data Index: 229317 (C4 (Web Text))

Max Activating Token Index: 344

Text #3

Max Range: 3.8478. Min Range: -3.8478

Max Act: 3.7852. Min Act: -0.1700

Data Index: 1039831 (C4 (Web Text))

Max Activating Token Index: 529

Text #4

Max Range: 3.8478. Min Range: -3.8478

Max Act: 3.7852. Min Act: -0.1700

Data Index: 682572 (C4 (Web Text))

Max Activating Token Index: 479

Text #5

Max Range: 3.8478. Min Range: -3.8478

Max Act: 3.6601. Min Act: -0.1700

Data Index: 413714 (C4 (Web Text))

Max Activating Token Index: 843

Text #6

Max Range: 3.8478. Min Range: -3.8478

Max Act: 3.7852. Min Act: -0.1700

Data Index: 1011071 (C4 (Web Text))

Max Activating Token Index: 624

Text #7

Max Range: 3.8478. Min Range: -3.8478

Max Act: 3.7227. Min Act: -0.1700

Data Index: 1002337 (C4 (Web Text))

Max Activating Token Index: 970

Text #8

Max Range: 3.8478. Min Range: -3.8478

Max Act: 3.7227. Min Act: -0.1700

Data Index: 195700 (C4 (Web Text))

Max Activating Token Index: 427

Text #9

Max Range: 3.8478. Min Range: -3.8478

Max Act: 3.6914. Min Act: -0.1700

Data Index: 1284098 (C4 (Web Text))

Max Activating Token Index: 858

Text #10

Max Range: 3.8478. Min Range: -3.8478

Max Act: 3.6914. Min Act: -0.1700

Data Index: 945223 (C4 (Web Text))

Max Activating Token Index: 309

Text #11

Max Range: 3.8478. Min Range: -3.8478

Max Act: 3.7227. Min Act: -0.1700

Data Index: 137678 (C4 (Web Text))

Max Activating Token Index: 602

Text #12

Max Range: 3.8478. Min Range: -3.8478

Max Act: 3.6914. Min Act: -0.1700

Data Index: 403394 (C4 (Web Text))

Max Activating Token Index: 290

Text #13

Max Range: 3.8478. Min Range: -3.8478

Max Act: 3.6914. Min Act: -0.1700

Data Index: 1142165 (C4 (Web Text))

Max Activating Token Index: 20

Text #14

Max Range: 3.8478. Min Range: -3.8478

Max Act: 3.7540. Min Act: -0.1700

Data Index: 417445 (C4 (Web Text))

Max Activating Token Index: 708

Text #15

Max Range: 3.8478. Min Range: -3.8478

Max Act: 3.6914. Min Act: -0.1700

Data Index: 1253029 (C4 (Web Text))

Max Activating Token Index: 694

Text #16

Max Range: 3.8478. Min Range: -3.8478

Max Act: 3.6601. Min Act: -0.1700

Data Index: 346080 (C4 (Web Text))

Max Activating Token Index: 470

Text #17

Max Range: 3.8478. Min Range: -3.8478

Max Act: 3.6288. Min Act: -0.1700

Data Index: 1121729 (C4 (Web Text))

Max Activating Token Index: 560

Text #18

Max Range: 3.8478. Min Range: -3.8478

Max Act: 3.5975. Min Act: -0.1700

Data Index: 129159 (C4 (Web Text))

Max Activating Token Index: 683

Text #19

Max Range: 3.8478. Min Range: -3.8478

Max Act: 3.6288. Min Act: -0.1700

Data Index: 710421 (C4 (Web Text))

Max Activating Token Index: 573