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

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

Neuron 829 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.9584. Min Range: -5.9584

Max Act: 5.9584. Min Act: -0.1700

Data Index: 1149258 (C4 (Web Text))

Max Activating Token Index: 700

Text #1

Max Range: 5.9584. Min Range: -5.9584

Max Act: 5.8334. Min Act: -0.1700

Data Index: 1149867 (C4 (Web Text))

Max Activating Token Index: 407

Text #2

Max Range: 5.9584. Min Range: -5.9584

Max Act: 5.8334. Min Act: -0.1700

Data Index: 1040205 (C4 (Web Text))

Max Activating Token Index: 403

Text #3

Max Range: 5.9584. Min Range: -5.9584

Max Act: 5.8334. Min Act: -0.1700

Data Index: 282016 (C4 (Web Text))

Max Activating Token Index: 751

Text #4

Max Range: 5.9584. Min Range: -5.9584

Max Act: 5.7709. Min Act: -0.1700

Data Index: 178039 (C4 (Web Text))

Max Activating Token Index: 780

Text #5

Max Range: 5.9584. Min Range: -5.9584

Max Act: 5.7084. Min Act: -0.1700

Data Index: 567104 (C4 (Web Text))

Max Activating Token Index: 753

Text #6

Max Range: 5.9584. Min Range: -5.9584

Max Act: 5.7396. Min Act: -0.1700

Data Index: 604397 (C4 (Web Text))

Max Activating Token Index: 331

Text #7

Max Range: 5.9584. Min Range: -5.9584

Max Act: 5.7396. Min Act: -0.1700

Data Index: 100992 (C4 (Web Text))

Max Activating Token Index: 620

Text #8

Max Range: 5.9584. Min Range: -5.9584

Max Act: 5.7084. Min Act: -0.1700

Data Index: 295970 (C4 (Web Text))

Max Activating Token Index: 157

Text #9

Max Range: 5.9584. Min Range: -5.9584

Max Act: 5.7084. Min Act: -0.1700

Data Index: 755847 (C4 (Web Text))

Max Activating Token Index: 844

Text #10

Max Range: 5.9584. Min Range: -5.9584

Max Act: 5.7084. Min Act: -0.1700

Data Index: 481543 (C4 (Web Text))

Max Activating Token Index: 454

Text #11

Max Range: 5.9584. Min Range: -5.9584

Max Act: 5.7084. Min Act: -0.1700

Data Index: 867263 (C4 (Web Text))

Max Activating Token Index: 704

Text #12

Max Range: 5.9584. Min Range: -5.9584

Max Act: 5.7084. Min Act: -0.1700

Data Index: 543514 (C4 (Web Text))

Max Activating Token Index: 503

Text #13

Max Range: 5.9584. Min Range: -5.9584

Max Act: 5.7084. Min Act: -0.1700

Data Index: 617930 (C4 (Web Text))

Max Activating Token Index: 1008

Text #14

Max Range: 5.9584. Min Range: -5.9584

Max Act: 5.6771. Min Act: -0.1700

Data Index: 1296397 (C4 (Web Text))

Max Activating Token Index: 919

Text #15

Max Range: 5.9584. Min Range: -5.9584

Max Act: 5.6771. Min Act: -0.1700

Data Index: 1116645 (C4 (Web Text))

Max Activating Token Index: 903

Text #16

Max Range: 5.9584. Min Range: -5.9584

Max Act: 5.6146. Min Act: -0.1700

Data Index: 525127 (C4 (Web Text))

Max Activating Token Index: 890

Text #17

Max Range: 5.9584. Min Range: -5.9584

Max Act: 5.5834. Min Act: -0.1700

Data Index: 753462 (C4 (Web Text))

Max Activating Token Index: 758

Text #18

Max Range: 5.9584. Min Range: -5.9584

Max Act: 5.5521. Min Act: -0.1700

Data Index: 222833 (C4 (Web Text))

Max Activating Token Index: 308

Text #19

Max Range: 5.9584. Min Range: -5.9584

Max Act: 5.6146. Min Act: -0.1700

Data Index: 537560 (C4 (Web Text))

Max Activating Token Index: 364