Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1891 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.8309. Min Range: -3.8309

Max Act: 3.7370. Min Act: -0.1700

Data Index: 80986 (C4 (Web Text))

Max Activating Token Index: 895

Text #1

Max Range: 3.8309. Min Range: -3.8309

Max Act: 3.7996. Min Act: -0.1700

Data Index: 509689 (C4 (Web Text))

Max Activating Token Index: 760

Text #2

Max Range: 3.8309. Min Range: -3.8309

Max Act: 3.7683. Min Act: -0.1700

Data Index: 661499 (C4 (Web Text))

Max Activating Token Index: 1000

Text #3

Max Range: 3.8309. Min Range: -3.8309

Max Act: 3.7683. Min Act: -0.1700

Data Index: 635593 (C4 (Web Text))

Max Activating Token Index: 668

Text #4

Max Range: 3.8309. Min Range: -3.8309

Max Act: 3.8309. Min Act: -0.1700

Data Index: 476968 (C4 (Web Text))

Max Activating Token Index: 879

Text #5

Max Range: 3.8309. Min Range: -3.8309

Max Act: 3.7057. Min Act: -0.1700

Data Index: 1177497 (C4 (Web Text))

Max Activating Token Index: 818

Text #6

Max Range: 3.8309. Min Range: -3.8309

Max Act: 3.6744. Min Act: -0.1700

Data Index: 64835 (C4 (Web Text))

Max Activating Token Index: 704

Text #7

Max Range: 3.8309. Min Range: -3.8309

Max Act: 3.7683. Min Act: -0.1700

Data Index: 565420 (C4 (Web Text))

Max Activating Token Index: 1020

Text #8

Max Range: 3.8309. Min Range: -3.8309

Max Act: 3.7057. Min Act: -0.1700

Data Index: 648566 (C4 (Web Text))

Max Activating Token Index: 552

Text #9

Max Range: 3.8309. Min Range: -3.8309

Max Act: 3.7057. Min Act: -0.1700

Data Index: 697070 (C4 (Web Text))

Max Activating Token Index: 433

Text #10

Max Range: 3.8309. Min Range: -3.8309

Max Act: 3.7370. Min Act: -0.1700

Data Index: 210578 (C4 (Web Text))

Max Activating Token Index: 482

Text #11

Max Range: 3.8309. Min Range: -3.8309

Max Act: 3.7057. Min Act: -0.1700

Data Index: 666953 (C4 (Web Text))

Max Activating Token Index: 397

Text #12

Max Range: 3.8309. Min Range: -3.8309

Max Act: 3.7057. Min Act: -0.1700

Data Index: 292460 (C4 (Web Text))

Max Activating Token Index: 1010

Text #13

Max Range: 3.8309. Min Range: -3.8309

Max Act: 3.6744. Min Act: -0.1700

Data Index: 49845 (C4 (Web Text))

Max Activating Token Index: 1002

Text #14

Max Range: 3.8309. Min Range: -3.8309

Max Act: 3.6431. Min Act: -0.1700

Data Index: 599466 (C4 (Web Text))

Max Activating Token Index: 999

Text #15

Max Range: 3.8309. Min Range: -3.8309

Max Act: 3.6744. Min Act: -0.1700

Data Index: 69690 (C4 (Web Text))

Max Activating Token Index: 428

Text #16

Max Range: 3.8309. Min Range: -3.8309

Max Act: 3.7057. Min Act: -0.1700

Data Index: 426305 (C4 (Web Text))

Max Activating Token Index: 825

Text #17

Max Range: 3.8309. Min Range: -3.8309

Max Act: 3.6744. Min Act: -0.1700

Data Index: 434301 (C4 (Web Text))

Max Activating Token Index: 627

Text #18

Max Range: 3.8309. Min Range: -3.8309

Max Act: 3.7370. Min Act: -0.1700

Data Index: 467544 (C4 (Web Text))

Max Activating Token Index: 598

Text #19

Max Range: 3.8309. Min Range: -3.8309

Max Act: 3.6744. Min Act: -0.1700

Data Index: 476279 (C4 (Web Text))

Max Activating Token Index: 1009