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

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

Neuron 79 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3630. Min Range: -3.3630

Max Act: 3.3473. Min Act: -0.1700

Data Index: 1216217 (C4 (Web Text))

Max Activating Token Index: 633

Text #1

Max Range: 3.3630. Min Range: -3.3630

Max Act: 3.3630. Min Act: -0.1700

Data Index: 467289 (C4 (Web Text))

Max Activating Token Index: 281

Text #2

Max Range: 3.3630. Min Range: -3.3630

Max Act: 3.3316. Min Act: -0.1700

Data Index: 444119 (C4 (Web Text))

Max Activating Token Index: 390

Text #3

Max Range: 3.3630. Min Range: -3.3630

Max Act: 3.3159. Min Act: -0.1700

Data Index: 558863 (C4 (Web Text))

Max Activating Token Index: 313

Text #4

Max Range: 3.3630. Min Range: -3.3630

Max Act: 3.3002. Min Act: -0.1700

Data Index: 943324 (C4 (Web Text))

Max Activating Token Index: 517

Text #5

Max Range: 3.3630. Min Range: -3.3630

Max Act: 3.3316. Min Act: -0.1700

Data Index: 754756 (C4 (Web Text))

Max Activating Token Index: 39

Text #6

Max Range: 3.3630. Min Range: -3.3630

Max Act: 3.3159. Min Act: -0.1700

Data Index: 145701 (C4 (Web Text))

Max Activating Token Index: 610

Text #7

Max Range: 3.3630. Min Range: -3.3630

Max Act: 3.2845. Min Act: -0.1700

Data Index: 1023175 (C4 (Web Text))

Max Activating Token Index: 982

Text #8

Max Range: 3.3630. Min Range: -3.3630

Max Act: 3.3002. Min Act: -0.1700

Data Index: 751683 (C4 (Web Text))

Max Activating Token Index: 501

Text #9

Max Range: 3.3630. Min Range: -3.3630

Max Act: 3.2845. Min Act: -0.1700

Data Index: 815752 (C4 (Web Text))

Max Activating Token Index: 834

Text #10

Max Range: 3.3630. Min Range: -3.3630

Max Act: 3.2845. Min Act: -0.1700

Data Index: 574115 (C4 (Web Text))

Max Activating Token Index: 564

Text #11

Max Range: 3.3630. Min Range: -3.3630

Max Act: 3.2688. Min Act: -0.1700

Data Index: 29042 (C4 (Web Text))

Max Activating Token Index: 2

Text #12

Max Range: 3.3630. Min Range: -3.3630

Max Act: 3.2373. Min Act: -0.1700

Data Index: 1012624 (C4 (Web Text))

Max Activating Token Index: 168

Text #13

Max Range: 3.3630. Min Range: -3.3630

Max Act: 3.2531. Min Act: -0.1700

Data Index: 776526 (C4 (Web Text))

Max Activating Token Index: 335

Text #14

Max Range: 3.3630. Min Range: -3.3630

Max Act: 3.2531. Min Act: -0.1700

Data Index: 747453 (C4 (Web Text))

Max Activating Token Index: 890

Text #15

Max Range: 3.3630. Min Range: -3.3630

Max Act: 3.2688. Min Act: -0.1700

Data Index: 109230 (C4 (Web Text))

Max Activating Token Index: 621

Text #16

Max Range: 3.3630. Min Range: -3.3630

Max Act: 3.2688. Min Act: -0.1700

Data Index: 812549 (C4 (Web Text))

Max Activating Token Index: 719

Text #17

Max Range: 3.3630. Min Range: -3.3630

Max Act: 3.2531. Min Act: -0.1700

Data Index: 1215958 (C4 (Web Text))

Max Activating Token Index: 756

Text #18

Max Range: 3.3630. Min Range: -3.3630

Max Act: 3.2216. Min Act: -0.1700

Data Index: 1009916 (C4 (Web Text))

Max Activating Token Index: 843

Text #19

Max Range: 3.3630. Min Range: -3.3630

Max Act: 3.1901. Min Act: -0.1700

Data Index: 18363 (C4 (Web Text))

Max Activating Token Index: 501