Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 416 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.2759. Min Range: -3.2759

Max Act: 3.2759. Min Act: -0.1700

Data Index: 320157 (C4 (Web Text))

Max Activating Token Index: 10

Text #1

Max Range: 3.2759. Min Range: -3.2759

Max Act: 3.2287. Min Act: -0.1700

Data Index: 291757 (C4 (Web Text))

Max Activating Token Index: 191

Text #2

Max Range: 3.2759. Min Range: -3.2759

Max Act: 3.2130. Min Act: -0.1700

Data Index: 873740 (C4 (Web Text))

Max Activating Token Index: 443

Text #3

Max Range: 3.2759. Min Range: -3.2759

Max Act: 3.1973. Min Act: -0.1700

Data Index: 55559 (C4 (Web Text))

Max Activating Token Index: 745

Text #4

Max Range: 3.2759. Min Range: -3.2759

Max Act: 3.1658. Min Act: -0.1700

Data Index: 71791 (C4 (Web Text))

Max Activating Token Index: 18

Text #5

Max Range: 3.2759. Min Range: -3.2759

Max Act: 3.1185. Min Act: -0.1700

Data Index: 553594 (C4 (Web Text))

Max Activating Token Index: 831

Text #6

Max Range: 3.2759. Min Range: -3.2759

Max Act: 3.1185. Min Act: -0.1700

Data Index: 818854 (C4 (Web Text))

Max Activating Token Index: 815

Text #7

Max Range: 3.2759. Min Range: -3.2759

Max Act: 3.1185. Min Act: -0.1700

Data Index: 1130887 (C4 (Web Text))

Max Activating Token Index: 978

Text #8

Max Range: 3.2759. Min Range: -3.2759

Max Act: 3.1028. Min Act: -0.1700

Data Index: 160399 (C4 (Web Text))

Max Activating Token Index: 927

Text #9

Max Range: 3.2759. Min Range: -3.2759

Max Act: 3.0712. Min Act: -0.1700

Data Index: 1046396 (C4 (Web Text))

Max Activating Token Index: 11

Text #10

Max Range: 3.2759. Min Range: -3.2759

Max Act: 3.0870. Min Act: -0.1700

Data Index: 982876 (C4 (Web Text))

Max Activating Token Index: 950

Text #11

Max Range: 3.2759. Min Range: -3.2759

Max Act: 3.0870. Min Act: -0.1700

Data Index: 11510 (C4 (Web Text))

Max Activating Token Index: 142

Text #12

Max Range: 3.2759. Min Range: -3.2759

Max Act: 3.0870. Min Act: -0.1700

Data Index: 275776 (C4 (Web Text))

Max Activating Token Index: 36

Text #13

Max Range: 3.2759. Min Range: -3.2759

Max Act: 3.0712. Min Act: -0.1700

Data Index: 1141052 (C4 (Web Text))

Max Activating Token Index: 592

Text #14

Max Range: 3.2759. Min Range: -3.2759

Max Act: 3.0712. Min Act: -0.1700

Data Index: 616783 (C4 (Web Text))

Max Activating Token Index: 16

Text #15

Max Range: 3.2759. Min Range: -3.2759

Max Act: 3.0555. Min Act: -0.1700

Data Index: 1239364 (C4 (Web Text))

Max Activating Token Index: 54

Text #16

Max Range: 3.2759. Min Range: -3.2759

Max Act: 3.0397. Min Act: -0.1700

Data Index: 95945 (C4 (Web Text))

Max Activating Token Index: 436

Text #17

Max Range: 3.2759. Min Range: -3.2759

Max Act: 3.0239. Min Act: -0.1700

Data Index: 779070 (C4 (Web Text))

Max Activating Token Index: 908

Text #18

Max Range: 3.2759. Min Range: -3.2759

Max Act: 3.0239. Min Act: -0.1700

Data Index: 773709 (C4 (Web Text))

Max Activating Token Index: 329

Text #19

Max Range: 3.2759. Min Range: -3.2759

Max Act: 3.0081. Min Act: -0.1700

Data Index: 953464 (C4 (Web Text))

Max Activating Token Index: 783