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

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

Neuron 694 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.7010. Min Range: -5.7010

Max Act: 5.7010. Min Act: -0.1700

Data Index: 230525 (C4 (Web Text))

Max Activating Token Index: 1016

Text #1

Max Range: 5.7010. Min Range: -5.7010

Max Act: 5.7010. Min Act: -0.1700

Data Index: 1267444 (C4 (Web Text))

Max Activating Token Index: 926

Text #2

Max Range: 5.7010. Min Range: -5.7010

Max Act: 5.6072. Min Act: -0.1700

Data Index: 602422 (C4 (Web Text))

Max Activating Token Index: 921

Text #3

Max Range: 5.7010. Min Range: -5.7010

Max Act: 5.6697. Min Act: -0.1700

Data Index: 1236780 (C4 (Web Text))

Max Activating Token Index: 899

Text #4

Max Range: 5.7010. Min Range: -5.7010

Max Act: 5.5447. Min Act: -0.1700

Data Index: 823096 (C4 (Web Text))

Max Activating Token Index: 958

Text #5

Max Range: 5.7010. Min Range: -5.7010

Max Act: 5.5135. Min Act: -0.1700

Data Index: 705133 (C4 (Web Text))

Max Activating Token Index: 737

Text #6

Max Range: 5.7010. Min Range: -5.7010

Max Act: 5.5447. Min Act: -0.1700

Data Index: 310359 (C4 (Web Text))

Max Activating Token Index: 527

Text #7

Max Range: 5.7010. Min Range: -5.7010

Max Act: 5.5135. Min Act: -0.1700

Data Index: 330055 (C4 (Web Text))

Max Activating Token Index: 371

Text #8

Max Range: 5.7010. Min Range: -5.7010

Max Act: 5.5447. Min Act: -0.1700

Data Index: 1090757 (C4 (Web Text))

Max Activating Token Index: 445

Text #9

Max Range: 5.7010. Min Range: -5.7010

Max Act: 5.4510. Min Act: -0.1700

Data Index: 806688 (C4 (Web Text))

Max Activating Token Index: 351

Text #10

Max Range: 5.7010. Min Range: -5.7010

Max Act: 5.3885. Min Act: -0.1700

Data Index: 784671 (C4 (Web Text))

Max Activating Token Index: 572

Text #11

Max Range: 5.7010. Min Range: -5.7010

Max Act: 5.2947. Min Act: -0.1700

Data Index: 174383 (C4 (Web Text))

Max Activating Token Index: 723

Text #12

Max Range: 5.7010. Min Range: -5.7010

Max Act: 5.2947. Min Act: -0.1700

Data Index: 585047 (C4 (Web Text))

Max Activating Token Index: 890

Text #13

Max Range: 5.7010. Min Range: -5.7010

Max Act: 5.2947. Min Act: -0.1700

Data Index: 688735 (C4 (Web Text))

Max Activating Token Index: 712

Text #14

Max Range: 5.7010. Min Range: -5.7010

Max Act: 5.2322. Min Act: -0.1700

Data Index: 486014 (C4 (Web Text))

Max Activating Token Index: 1016

Text #15

Max Range: 5.7010. Min Range: -5.7010

Max Act: 5.2947. Min Act: -0.1700

Data Index: 40740 (C4 (Web Text))

Max Activating Token Index: 848

Text #16

Max Range: 5.7010. Min Range: -5.7010

Max Act: 5.2635. Min Act: -0.1700

Data Index: 569106 (C4 (Web Text))

Max Activating Token Index: 749

Text #17

Max Range: 5.7010. Min Range: -5.7010

Max Act: 5.2322. Min Act: -0.1700

Data Index: 16375 (C4 (Web Text))

Max Activating Token Index: 283

Text #18

Max Range: 5.7010. Min Range: -5.7010

Max Act: 5.2010. Min Act: -0.1700

Data Index: 38681 (C4 (Web Text))

Max Activating Token Index: 695

Text #19

Max Range: 5.7010. Min Range: -5.7010

Max Act: 5.2010. Min Act: -0.1700

Data Index: 935043 (C4 (Web Text))

Max Activating Token Index: 931