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

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

Neuron 1237 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: 3.1362. Min Range: -3.1362

Max Act: 3.1362. Min Act: -0.1700

Data Index: 203899 (C4 (Web Text))

Max Activating Token Index: 781

Text #1

Max Range: 3.1362. Min Range: -3.1362

Max Act: 3.1362. Min Act: -0.1700

Data Index: 198024 (C4 (Web Text))

Max Activating Token Index: 945

Text #2

Max Range: 3.1362. Min Range: -3.1362

Max Act: 3.1362. Min Act: -0.1700

Data Index: 69011 (C4 (Web Text))

Max Activating Token Index: 717

Text #3

Max Range: 3.1362. Min Range: -3.1362

Max Act: 3.1362. Min Act: -0.1700

Data Index: 1261856 (C4 (Web Text))

Max Activating Token Index: 568

Text #4

Max Range: 3.1362. Min Range: -3.1362

Max Act: 3.1047. Min Act: -0.1700

Data Index: 543769 (C4 (Web Text))

Max Activating Token Index: 326

Text #5

Max Range: 3.1362. Min Range: -3.1362

Max Act: 3.1205. Min Act: -0.1700

Data Index: 75915 (C4 (Web Text))

Max Activating Token Index: 141

Text #6

Max Range: 3.1362. Min Range: -3.1362

Max Act: 3.1362. Min Act: -0.1700

Data Index: 1186914 (C4 (Web Text))

Max Activating Token Index: 79

Text #7

Max Range: 3.1362. Min Range: -3.1362

Max Act: 3.0889. Min Act: -0.1700

Data Index: 1194855 (C4 (Web Text))

Max Activating Token Index: 187

Text #8

Max Range: 3.1362. Min Range: -3.1362

Max Act: 3.1047. Min Act: -0.1700

Data Index: 252677 (C4 (Web Text))

Max Activating Token Index: 871

Text #9

Max Range: 3.1362. Min Range: -3.1362

Max Act: 3.0889. Min Act: -0.1700

Data Index: 21875 (C4 (Web Text))

Max Activating Token Index: 209

Text #10

Max Range: 3.1362. Min Range: -3.1362

Max Act: 3.1047. Min Act: -0.1700

Data Index: 746051 (C4 (Web Text))

Max Activating Token Index: 825

Text #11

Max Range: 3.1362. Min Range: -3.1362

Max Act: 3.0889. Min Act: -0.1700

Data Index: 1330450 (C4 (Web Text))

Max Activating Token Index: 694

Text #12

Max Range: 3.1362. Min Range: -3.1362

Max Act: 3.0889. Min Act: -0.1700

Data Index: 985895 (C4 (Web Text))

Max Activating Token Index: 831

Text #13

Max Range: 3.1362. Min Range: -3.1362

Max Act: 3.1047. Min Act: -0.1700

Data Index: 514836 (C4 (Web Text))

Max Activating Token Index: 850

Text #14

Max Range: 3.1362. Min Range: -3.1362

Max Act: 3.1047. Min Act: -0.1700

Data Index: 594514 (C4 (Web Text))

Max Activating Token Index: 733

Text #15

Max Range: 3.1362. Min Range: -3.1362

Max Act: 3.0889. Min Act: -0.1700

Data Index: 248021 (C4 (Web Text))

Max Activating Token Index: 1001

Text #16

Max Range: 3.1362. Min Range: -3.1362

Max Act: 3.1047. Min Act: -0.1700

Data Index: 596966 (C4 (Web Text))

Max Activating Token Index: 1015

Text #17

Max Range: 3.1362. Min Range: -3.1362

Max Act: 3.0889. Min Act: -0.1700

Data Index: 55817 (C4 (Web Text))

Max Activating Token Index: 650

Text #18

Max Range: 3.1362. Min Range: -3.1362

Max Act: 3.0889. Min Act: -0.1700

Data Index: 1188309 (C4 (Web Text))

Max Activating Token Index: 822

Text #19

Max Range: 3.1362. Min Range: -3.1362

Max Act: 3.0732. Min Act: -0.1700

Data Index: 446593 (C4 (Web Text))

Max Activating Token Index: 697