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

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

Neuron 1594 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: 5.2431. Min Range: -5.2431

Max Act: 5.2119. Min Act: -0.1700

Data Index: 1044061 (C4 (Web Text))

Max Activating Token Index: 52

Text #1

Max Range: 5.2431. Min Range: -5.2431

Max Act: 5.2431. Min Act: -0.1700

Data Index: 860602 (C4 (Web Text))

Max Activating Token Index: 76

Text #2

Max Range: 5.2431. Min Range: -5.2431

Max Act: 5.0869. Min Act: -0.1700

Data Index: 1083715 (C4 (Web Text))

Max Activating Token Index: 910

Text #3

Max Range: 5.2431. Min Range: -5.2431

Max Act: 5.0556. Min Act: -0.1700

Data Index: 1022734 (C4 (Web Text))

Max Activating Token Index: 56

Text #4

Max Range: 5.2431. Min Range: -5.2431

Max Act: 4.9306. Min Act: -0.1700

Data Index: 918419 (C4 (Web Text))

Max Activating Token Index: 890

Text #5

Max Range: 5.2431. Min Range: -5.2431

Max Act: 4.9306. Min Act: -0.1700

Data Index: 112462 (C4 (Web Text))

Max Activating Token Index: 733

Text #6

Max Range: 5.2431. Min Range: -5.2431

Max Act: 4.7744. Min Act: -0.1700

Data Index: 637125 (C4 (Web Text))

Max Activating Token Index: 449

Text #7

Max Range: 5.2431. Min Range: -5.2431

Max Act: 4.7744. Min Act: -0.1700

Data Index: 790795 (C4 (Web Text))

Max Activating Token Index: 481

Text #8

Max Range: 5.2431. Min Range: -5.2431

Max Act: 4.7744. Min Act: -0.1700

Data Index: 889145 (C4 (Web Text))

Max Activating Token Index: 179

Text #9

Max Range: 5.2431. Min Range: -5.2431

Max Act: 4.6494. Min Act: -0.1700

Data Index: 433886 (C4 (Web Text))

Max Activating Token Index: 789

Text #10

Max Range: 5.2431. Min Range: -5.2431

Max Act: 4.8681. Min Act: -0.1700

Data Index: 441886 (C4 (Web Text))

Max Activating Token Index: 444

Text #11

Max Range: 5.2431. Min Range: -5.2431

Max Act: 4.8056. Min Act: -0.1700

Data Index: 814699 (C4 (Web Text))

Max Activating Token Index: 873

Text #12

Max Range: 5.2431. Min Range: -5.2431

Max Act: 4.7431. Min Act: -0.1700

Data Index: 586695 (C4 (Web Text))

Max Activating Token Index: 112

Text #13

Max Range: 5.2431. Min Range: -5.2431

Max Act: 4.7119. Min Act: -0.1700

Data Index: 59029 (C4 (Web Text))

Max Activating Token Index: 284

Text #14

Max Range: 5.2431. Min Range: -5.2431

Max Act: 4.7431. Min Act: -0.1700

Data Index: 689010 (C4 (Web Text))

Max Activating Token Index: 162

Text #15

Max Range: 5.2431. Min Range: -5.2431

Max Act: 4.7744. Min Act: -0.1700

Data Index: 18872 (C4 (Web Text))

Max Activating Token Index: 472

Text #16

Max Range: 5.2431. Min Range: -5.2431

Max Act: 4.7744. Min Act: -0.1700

Data Index: 1289824 (C4 (Web Text))

Max Activating Token Index: 569

Text #17

Max Range: 5.2431. Min Range: -5.2431

Max Act: 4.6806. Min Act: -0.1700

Data Index: 83128 (C4 (Web Text))

Max Activating Token Index: 192

Text #18

Max Range: 5.2431. Min Range: -5.2431

Max Act: 4.7119. Min Act: -0.1700

Data Index: 1142041 (C4 (Web Text))

Max Activating Token Index: 947

Text #19

Max Range: 5.2431. Min Range: -5.2431

Max Act: 4.6806. Min Act: -0.1700

Data Index: 1182490 (C4 (Web Text))

Max Activating Token Index: 339