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

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

Neuron 1124 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: 5.2057. Min Range: -5.2057

Max Act: 5.2057. Min Act: -0.1700

Data Index: 708385 (C4 (Web Text))

Max Activating Token Index: 829

Text #1

Max Range: 5.2057. Min Range: -5.2057

Max Act: 5.1432. Min Act: -0.1700

Data Index: 1174139 (C4 (Web Text))

Max Activating Token Index: 948

Text #2

Max Range: 5.2057. Min Range: -5.2057

Max Act: 5.1432. Min Act: -0.1700

Data Index: 211195 (C4 (Web Text))

Max Activating Token Index: 942

Text #3

Max Range: 5.2057. Min Range: -5.2057

Max Act: 5.1432. Min Act: -0.1700

Data Index: 1069931 (C4 (Web Text))

Max Activating Token Index: 662

Text #4

Max Range: 5.2057. Min Range: -5.2057

Max Act: 5.0807. Min Act: -0.1700

Data Index: 565603 (C4 (Web Text))

Max Activating Token Index: 817

Text #5

Max Range: 5.2057. Min Range: -5.2057

Max Act: 5.1432. Min Act: -0.1700

Data Index: 1283252 (C4 (Web Text))

Max Activating Token Index: 718

Text #6

Max Range: 5.2057. Min Range: -5.2057

Max Act: 5.1432. Min Act: -0.1700

Data Index: 342940 (C4 (Web Text))

Max Activating Token Index: 891

Text #7

Max Range: 5.2057. Min Range: -5.2057

Max Act: 5.0495. Min Act: -0.1700

Data Index: 779228 (C4 (Web Text))

Max Activating Token Index: 579

Text #8

Max Range: 5.2057. Min Range: -5.2057

Max Act: 5.1120. Min Act: -0.1700

Data Index: 95959 (C4 (Web Text))

Max Activating Token Index: 892

Text #9

Max Range: 5.2057. Min Range: -5.2057

Max Act: 5.1120. Min Act: -0.1700

Data Index: 1152464 (C4 (Web Text))

Max Activating Token Index: 824

Text #10

Max Range: 5.2057. Min Range: -5.2057

Max Act: 5.0807. Min Act: -0.1700

Data Index: 920973 (C4 (Web Text))

Max Activating Token Index: 715

Text #11

Max Range: 5.2057. Min Range: -5.2057

Max Act: 5.0495. Min Act: -0.1700

Data Index: 190071 (C4 (Web Text))

Max Activating Token Index: 166

Text #12

Max Range: 5.2057. Min Range: -5.2057

Max Act: 5.0807. Min Act: -0.1700

Data Index: 721369 (C4 (Web Text))

Max Activating Token Index: 893

Text #13

Max Range: 5.2057. Min Range: -5.2057

Max Act: 5.0495. Min Act: -0.1700

Data Index: 687119 (C4 (Web Text))

Max Activating Token Index: 954

Text #14

Max Range: 5.2057. Min Range: -5.2057

Max Act: 4.9245. Min Act: -0.1700

Data Index: 532533 (C4 (Web Text))

Max Activating Token Index: 585

Text #15

Max Range: 5.2057. Min Range: -5.2057

Max Act: 5.0182. Min Act: -0.1700

Data Index: 339144 (C4 (Web Text))

Max Activating Token Index: 878

Text #16

Max Range: 5.2057. Min Range: -5.2057

Max Act: 5.0807. Min Act: -0.1700

Data Index: 177384 (C4 (Web Text))

Max Activating Token Index: 504

Text #17

Max Range: 5.2057. Min Range: -5.2057

Max Act: 5.0182. Min Act: -0.1700

Data Index: 1034244 (C4 (Web Text))

Max Activating Token Index: 720

Text #18

Max Range: 5.2057. Min Range: -5.2057

Max Act: 5.0495. Min Act: -0.1700

Data Index: 159211 (C4 (Web Text))

Max Activating Token Index: 298

Text #19

Max Range: 5.2057. Min Range: -5.2057

Max Act: 5.0182. Min Act: -0.1700

Data Index: 481136 (C4 (Web Text))

Max Activating Token Index: 518