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

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

Neuron 1699 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8840. Min Range: -3.8840

Max Act: 3.8840. Min Act: -0.1700

Data Index: 770 (C4 (Web Text))

Max Activating Token Index: 141

Text #1

Max Range: 3.8840. Min Range: -3.8840

Max Act: 3.8058. Min Act: -0.1700

Data Index: 1306719 (C4 (Web Text))

Max Activating Token Index: 163

Text #2

Max Range: 3.8840. Min Range: -3.8840

Max Act: 3.8214. Min Act: -0.1700

Data Index: 782824 (C4 (Web Text))

Max Activating Token Index: 31

Text #3

Max Range: 3.8840. Min Range: -3.8840

Max Act: 3.8371. Min Act: -0.1700

Data Index: 157395 (C4 (Web Text))

Max Activating Token Index: 670

Text #4

Max Range: 3.8840. Min Range: -3.8840

Max Act: 3.7745. Min Act: -0.1700

Data Index: 986897 (C4 (Web Text))

Max Activating Token Index: 147

Text #5

Max Range: 3.8840. Min Range: -3.8840

Max Act: 3.7432. Min Act: -0.1700

Data Index: 455708 (C4 (Web Text))

Max Activating Token Index: 817

Text #6

Max Range: 3.8840. Min Range: -3.8840

Max Act: 3.7745. Min Act: -0.1700

Data Index: 1354307 (C4 (Web Text))

Max Activating Token Index: 21

Text #7

Max Range: 3.8840. Min Range: -3.8840

Max Act: 3.7745. Min Act: -0.1700

Data Index: 470455 (C4 (Web Text))

Max Activating Token Index: 888

Text #8

Max Range: 3.8840. Min Range: -3.8840

Max Act: 3.7119. Min Act: -0.1700

Data Index: 893091 (C4 (Web Text))

Max Activating Token Index: 473

Text #9

Max Range: 3.8840. Min Range: -3.8840

Max Act: 3.7432. Min Act: -0.1700

Data Index: 1312883 (C4 (Web Text))

Max Activating Token Index: 831

Text #10

Max Range: 3.8840. Min Range: -3.8840

Max Act: 3.7276. Min Act: -0.1700

Data Index: 905875 (C4 (Web Text))

Max Activating Token Index: 34

Text #11

Max Range: 3.8840. Min Range: -3.8840

Max Act: 3.7119. Min Act: -0.1700

Data Index: 1116585 (C4 (Web Text))

Max Activating Token Index: 87

Text #12

Max Range: 3.8840. Min Range: -3.8840

Max Act: 3.7119. Min Act: -0.1700

Data Index: 664347 (C4 (Web Text))

Max Activating Token Index: 56

Text #13

Max Range: 3.8840. Min Range: -3.8840

Max Act: 3.6493. Min Act: -0.1700

Data Index: 1034925 (C4 (Web Text))

Max Activating Token Index: 959

Text #14

Max Range: 3.8840. Min Range: -3.8840

Max Act: 3.6963. Min Act: -0.1700

Data Index: 531859 (C4 (Web Text))

Max Activating Token Index: 154

Text #15

Max Range: 3.8840. Min Range: -3.8840

Max Act: 3.6806. Min Act: -0.1700

Data Index: 1125406 (C4 (Web Text))

Max Activating Token Index: 942

Text #16

Max Range: 3.8840. Min Range: -3.8840

Max Act: 3.6337. Min Act: -0.1700

Data Index: 1132536 (C4 (Web Text))

Max Activating Token Index: 842

Text #17

Max Range: 3.8840. Min Range: -3.8840

Max Act: 3.6493. Min Act: -0.1700

Data Index: 965908 (C4 (Web Text))

Max Activating Token Index: 412

Text #18

Max Range: 3.8840. Min Range: -3.8840

Max Act: 3.6963. Min Act: -0.1700

Data Index: 1119044 (C4 (Web Text))

Max Activating Token Index: 553

Text #19

Max Range: 3.8840. Min Range: -3.8840

Max Act: 3.6337. Min Act: -0.1700

Data Index: 1030736 (C4 (Web Text))

Max Activating Token Index: 813