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

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

Neuron 277 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: 5.9984. Min Range: -5.9984

Max Act: 5.9046. Min Act: -0.1700

Data Index: 942978 (C4 (Web Text))

Max Activating Token Index: 774

Text #1

Max Range: 5.9984. Min Range: -5.9984

Max Act: 5.9984. Min Act: -0.1700

Data Index: 1034724 (C4 (Web Text))

Max Activating Token Index: 827

Text #2

Max Range: 5.9984. Min Range: -5.9984

Max Act: 5.8734. Min Act: -0.1700

Data Index: 745956 (C4 (Web Text))

Max Activating Token Index: 242

Text #3

Max Range: 5.9984. Min Range: -5.9984

Max Act: 5.8109. Min Act: -0.1700

Data Index: 509157 (C4 (Web Text))

Max Activating Token Index: 1020

Text #4

Max Range: 5.9984. Min Range: -5.9984

Max Act: 5.8734. Min Act: -0.1700

Data Index: 1160137 (C4 (Web Text))

Max Activating Token Index: 78

Text #5

Max Range: 5.9984. Min Range: -5.9984

Max Act: 5.7484. Min Act: -0.1700

Data Index: 773680 (C4 (Web Text))

Max Activating Token Index: 1013

Text #6

Max Range: 5.9984. Min Range: -5.9984

Max Act: 5.8109. Min Act: -0.1700

Data Index: 708009 (C4 (Web Text))

Max Activating Token Index: 65

Text #7

Max Range: 5.9984. Min Range: -5.9984

Max Act: 5.7796. Min Act: -0.1700

Data Index: 854863 (C4 (Web Text))

Max Activating Token Index: 405

Text #8

Max Range: 5.9984. Min Range: -5.9984

Max Act: 5.7796. Min Act: -0.1700

Data Index: 154860 (C4 (Web Text))

Max Activating Token Index: 204

Text #9

Max Range: 5.9984. Min Range: -5.9984

Max Act: 5.8109. Min Act: -0.1700

Data Index: 1314105 (C4 (Web Text))

Max Activating Token Index: 662

Text #10

Max Range: 5.9984. Min Range: -5.9984

Max Act: 5.8109. Min Act: -0.1700

Data Index: 412754 (C4 (Web Text))

Max Activating Token Index: 765

Text #11

Max Range: 5.9984. Min Range: -5.9984

Max Act: 5.8734. Min Act: -0.1700

Data Index: 514543 (C4 (Web Text))

Max Activating Token Index: 1005

Text #12

Max Range: 5.9984. Min Range: -5.9984

Max Act: 5.7796. Min Act: -0.1700

Data Index: 1137772 (C4 (Web Text))

Max Activating Token Index: 420

Text #13

Max Range: 5.9984. Min Range: -5.9984

Max Act: 5.8734. Min Act: -0.1700

Data Index: 1077787 (C4 (Web Text))

Max Activating Token Index: 667

Text #14

Max Range: 5.9984. Min Range: -5.9984

Max Act: 5.7796. Min Act: -0.1700

Data Index: 437581 (C4 (Web Text))

Max Activating Token Index: 761

Text #15

Max Range: 5.9984. Min Range: -5.9984

Max Act: 5.7796. Min Act: -0.1700

Data Index: 1011836 (C4 (Web Text))

Max Activating Token Index: 856

Text #16

Max Range: 5.9984. Min Range: -5.9984

Max Act: 5.7484. Min Act: -0.1700

Data Index: 1000142 (C4 (Web Text))

Max Activating Token Index: 1013

Text #17

Max Range: 5.9984. Min Range: -5.9984

Max Act: 5.6859. Min Act: -0.1700

Data Index: 1246669 (C4 (Web Text))

Max Activating Token Index: 684

Text #18

Max Range: 5.9984. Min Range: -5.9984

Max Act: 5.7484. Min Act: -0.1700

Data Index: 1225139 (C4 (Web Text))

Max Activating Token Index: 408

Text #19

Max Range: 5.9984. Min Range: -5.9984

Max Act: 5.7171. Min Act: -0.1700

Data Index: 842167 (C4 (Web Text))

Max Activating Token Index: 166