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

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

Neuron 1996 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: 4.0013. Min Range: -4.0013

Max Act: 4.0013. Min Act: -0.1700

Data Index: 921840 (C4 (Web Text))

Max Activating Token Index: 836

Text #1

Max Range: 4.0013. Min Range: -4.0013

Max Act: 3.9075. Min Act: -0.1700

Data Index: 1161631 (C4 (Web Text))

Max Activating Token Index: 457

Text #2

Max Range: 4.0013. Min Range: -4.0013

Max Act: 3.7511. Min Act: -0.1700

Data Index: 304319 (C4 (Web Text))

Max Activating Token Index: 935

Text #3

Max Range: 4.0013. Min Range: -4.0013

Max Act: 3.8136. Min Act: -0.1700

Data Index: 446207 (C4 (Web Text))

Max Activating Token Index: 125

Text #4

Max Range: 4.0013. Min Range: -4.0013

Max Act: 3.7823. Min Act: -0.1700

Data Index: 760343 (C4 (Web Text))

Max Activating Token Index: 809

Text #5

Max Range: 4.0013. Min Range: -4.0013

Max Act: 3.8136. Min Act: -0.1700

Data Index: 310590 (C4 (Web Text))

Max Activating Token Index: 897

Text #6

Max Range: 4.0013. Min Range: -4.0013

Max Act: 3.7511. Min Act: -0.1700

Data Index: 1408557 (Python Code)

Max Activating Token Index: 933

Text #7

Max Range: 4.0013. Min Range: -4.0013

Max Act: 3.7198. Min Act: -0.1700

Data Index: 579070 (C4 (Web Text))

Max Activating Token Index: 660

Text #8

Max Range: 4.0013. Min Range: -4.0013

Max Act: 3.7823. Min Act: -0.1700

Data Index: 1092822 (C4 (Web Text))

Max Activating Token Index: 781

Text #9

Max Range: 4.0013. Min Range: -4.0013

Max Act: 3.7198. Min Act: -0.1700

Data Index: 119421 (C4 (Web Text))

Max Activating Token Index: 710

Text #10

Max Range: 4.0013. Min Range: -4.0013

Max Act: 3.6885. Min Act: -0.1700

Data Index: 121588 (C4 (Web Text))

Max Activating Token Index: 851

Text #11

Max Range: 4.0013. Min Range: -4.0013

Max Act: 3.6885. Min Act: -0.1700

Data Index: 634867 (C4 (Web Text))

Max Activating Token Index: 893

Text #12

Max Range: 4.0013. Min Range: -4.0013

Max Act: 3.7511. Min Act: -0.1700

Data Index: 859084 (C4 (Web Text))

Max Activating Token Index: 422

Text #13

Max Range: 4.0013. Min Range: -4.0013

Max Act: 3.7511. Min Act: -0.1700

Data Index: 845575 (C4 (Web Text))

Max Activating Token Index: 78

Text #14

Max Range: 4.0013. Min Range: -4.0013

Max Act: 3.6102. Min Act: -0.1700

Data Index: 162630 (C4 (Web Text))

Max Activating Token Index: 863

Text #15

Max Range: 4.0013. Min Range: -4.0013

Max Act: 3.6572. Min Act: -0.1700

Data Index: 1002036 (C4 (Web Text))

Max Activating Token Index: 862

Text #16

Max Range: 4.0013. Min Range: -4.0013

Max Act: 3.7198. Min Act: -0.1700

Data Index: 50260 (C4 (Web Text))

Max Activating Token Index: 535

Text #17

Max Range: 4.0013. Min Range: -4.0013

Max Act: 3.7198. Min Act: -0.1700

Data Index: 126006 (C4 (Web Text))

Max Activating Token Index: 747

Text #18

Max Range: 4.0013. Min Range: -4.0013

Max Act: 3.6885. Min Act: -0.1700

Data Index: 574304 (C4 (Web Text))

Max Activating Token Index: 453

Text #19

Max Range: 4.0013. Min Range: -4.0013

Max Act: 3.6885. Min Act: -0.1700

Data Index: 1596848 (Python Code)

Max Activating Token Index: 229