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

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

Neuron 1812 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: 3.6885. Min Range: -3.6885

Max Act: 3.6885. Min Act: -0.1700

Data Index: 144198 (C4 (Web Text))

Max Activating Token Index: 657

Text #1

Max Range: 3.6885. Min Range: -3.6885

Max Act: 3.6885. Min Act: -0.1700

Data Index: 1210236 (C4 (Web Text))

Max Activating Token Index: 503

Text #2

Max Range: 3.6885. Min Range: -3.6885

Max Act: 3.6885. Min Act: -0.1700

Data Index: 1144791 (C4 (Web Text))

Max Activating Token Index: 778

Text #3

Max Range: 3.6885. Min Range: -3.6885

Max Act: 3.5946. Min Act: -0.1700

Data Index: 291363 (C4 (Web Text))

Max Activating Token Index: 884

Text #4

Max Range: 3.6885. Min Range: -3.6885

Max Act: 3.6416. Min Act: -0.1700

Data Index: 368833 (C4 (Web Text))

Max Activating Token Index: 500

Text #5

Max Range: 3.6885. Min Range: -3.6885

Max Act: 3.6259. Min Act: -0.1700

Data Index: 1016174 (C4 (Web Text))

Max Activating Token Index: 495

Text #6

Max Range: 3.6885. Min Range: -3.6885

Max Act: 3.6259. Min Act: -0.1700

Data Index: 141413 (C4 (Web Text))

Max Activating Token Index: 855

Text #7

Max Range: 3.6885. Min Range: -3.6885

Max Act: 3.5789. Min Act: -0.1700

Data Index: 832775 (C4 (Web Text))

Max Activating Token Index: 349

Text #8

Max Range: 3.6885. Min Range: -3.6885

Max Act: 3.5789. Min Act: -0.1700

Data Index: 531447 (C4 (Web Text))

Max Activating Token Index: 702

Text #9

Max Range: 3.6885. Min Range: -3.6885

Max Act: 3.6102. Min Act: -0.1700

Data Index: 1312622 (C4 (Web Text))

Max Activating Token Index: 142

Text #10

Max Range: 3.6885. Min Range: -3.6885

Max Act: 3.6102. Min Act: -0.1700

Data Index: 1127884 (C4 (Web Text))

Max Activating Token Index: 806

Text #11

Max Range: 3.6885. Min Range: -3.6885

Max Act: 3.5476. Min Act: -0.1700

Data Index: 291080 (C4 (Web Text))

Max Activating Token Index: 574

Text #12

Max Range: 3.6885. Min Range: -3.6885

Max Act: 3.5789. Min Act: -0.1700

Data Index: 929316 (C4 (Web Text))

Max Activating Token Index: 849

Text #13

Max Range: 3.6885. Min Range: -3.6885

Max Act: 3.5633. Min Act: -0.1700

Data Index: 65469 (C4 (Web Text))

Max Activating Token Index: 81

Text #14

Max Range: 3.6885. Min Range: -3.6885

Max Act: 3.5633. Min Act: -0.1700

Data Index: 955608 (C4 (Web Text))

Max Activating Token Index: 187

Text #15

Max Range: 3.6885. Min Range: -3.6885

Max Act: 3.5163. Min Act: -0.1700

Data Index: 966498 (C4 (Web Text))

Max Activating Token Index: 134

Text #16

Max Range: 3.6885. Min Range: -3.6885

Max Act: 3.5319. Min Act: -0.1700

Data Index: 977825 (C4 (Web Text))

Max Activating Token Index: 773

Text #17

Max Range: 3.6885. Min Range: -3.6885

Max Act: 3.5006. Min Act: -0.1700

Data Index: 73471 (C4 (Web Text))

Max Activating Token Index: 46

Text #18

Max Range: 3.6885. Min Range: -3.6885

Max Act: 3.5476. Min Act: -0.1700

Data Index: 529405 (C4 (Web Text))

Max Activating Token Index: 875

Text #19

Max Range: 3.6885. Min Range: -3.6885

Max Act: 3.5319. Min Act: -0.1700

Data Index: 305884 (C4 (Web Text))

Max Activating Token Index: 684