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

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

Neuron 1734 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1782. Min Range: -3.1782

Max Act: 3.1782. Min Act: -0.1700

Data Index: 1021250 (C4 (Web Text))

Max Activating Token Index: 9

Text #1

Max Range: 3.1782. Min Range: -3.1782

Max Act: 3.1782. Min Act: -0.1700

Data Index: 94899 (C4 (Web Text))

Max Activating Token Index: 2

Text #2

Max Range: 3.1782. Min Range: -3.1782

Max Act: 3.1467. Min Act: -0.1700

Data Index: 838843 (C4 (Web Text))

Max Activating Token Index: 906

Text #3

Max Range: 3.1782. Min Range: -3.1782

Max Act: 3.1467. Min Act: -0.1700

Data Index: 66210 (C4 (Web Text))

Max Activating Token Index: 742

Text #4

Max Range: 3.1782. Min Range: -3.1782

Max Act: 3.1309. Min Act: -0.1700

Data Index: 606120 (C4 (Web Text))

Max Activating Token Index: 20

Text #5

Max Range: 3.1782. Min Range: -3.1782

Max Act: 3.1467. Min Act: -0.1700

Data Index: 597939 (C4 (Web Text))

Max Activating Token Index: 71

Text #6

Max Range: 3.1782. Min Range: -3.1782

Max Act: 3.1152. Min Act: -0.1700

Data Index: 1342623 (C4 (Web Text))

Max Activating Token Index: 6

Text #7

Max Range: 3.1782. Min Range: -3.1782

Max Act: 3.0994. Min Act: -0.1700

Data Index: 34073 (C4 (Web Text))

Max Activating Token Index: 915

Text #8

Max Range: 3.1782. Min Range: -3.1782

Max Act: 3.1152. Min Act: -0.1700

Data Index: 860470 (C4 (Web Text))

Max Activating Token Index: 912

Text #9

Max Range: 3.1782. Min Range: -3.1782

Max Act: 3.0994. Min Act: -0.1700

Data Index: 892423 (C4 (Web Text))

Max Activating Token Index: 842

Text #10

Max Range: 3.1782. Min Range: -3.1782

Max Act: 3.1152. Min Act: -0.1700

Data Index: 818804 (C4 (Web Text))

Max Activating Token Index: 200

Text #11

Max Range: 3.1782. Min Range: -3.1782

Max Act: 3.1152. Min Act: -0.1700

Data Index: 1069793 (C4 (Web Text))

Max Activating Token Index: 178

Text #12

Max Range: 3.1782. Min Range: -3.1782

Max Act: 3.0678. Min Act: -0.1700

Data Index: 1291344 (C4 (Web Text))

Max Activating Token Index: 686

Text #13

Max Range: 3.1782. Min Range: -3.1782

Max Act: 3.0836. Min Act: -0.1700

Data Index: 1017553 (C4 (Web Text))

Max Activating Token Index: 898

Text #14

Max Range: 3.1782. Min Range: -3.1782

Max Act: 3.0678. Min Act: -0.1700

Data Index: 399595 (C4 (Web Text))

Max Activating Token Index: 956

Text #15

Max Range: 3.1782. Min Range: -3.1782

Max Act: 3.0521. Min Act: -0.1700

Data Index: 366679 (C4 (Web Text))

Max Activating Token Index: 305

Text #16

Max Range: 3.1782. Min Range: -3.1782

Max Act: 3.0678. Min Act: -0.1700

Data Index: 156783 (C4 (Web Text))

Max Activating Token Index: 287

Text #17

Max Range: 3.1782. Min Range: -3.1782

Max Act: 3.0521. Min Act: -0.1700

Data Index: 218921 (C4 (Web Text))

Max Activating Token Index: 286

Text #18

Max Range: 3.1782. Min Range: -3.1782

Max Act: 3.0521. Min Act: -0.1700

Data Index: 779870 (C4 (Web Text))

Max Activating Token Index: 152

Text #19

Max Range: 3.1782. Min Range: -3.1782

Max Act: 3.0521. Min Act: -0.1700

Data Index: 1145114 (C4 (Web Text))

Max Activating Token Index: 151