Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1669 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 6.1559. Min Range: -6.1559
Max Act: 6.1559. Min Act: -0.1700
Data Index: 1030674 (C4 (Web Text))
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1559. Min Range: -6.1559
Max Act: 5.8746. Min Act: -0.1700
Data Index: 32058 (C4 (Web Text))
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1559. Min Range: -6.1559
Max Act: 5.9059. Min Act: -0.1700
Data Index: 926239 (C4 (Web Text))
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1559. Min Range: -6.1559
Max Act: 5.8121. Min Act: -0.1700
Data Index: 1319701 (C4 (Web Text))
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1559. Min Range: -6.1559
Max Act: 5.8746. Min Act: -0.1700
Data Index: 113978 (C4 (Web Text))
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1559. Min Range: -6.1559
Max Act: 5.8434. Min Act: -0.1700
Data Index: 831466 (C4 (Web Text))
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1559. Min Range: -6.1559
Max Act: 5.8121. Min Act: -0.1700
Data Index: 638055 (C4 (Web Text))
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1559. Min Range: -6.1559
Max Act: 5.7809. Min Act: -0.1700
Data Index: 648959 (C4 (Web Text))
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1559. Min Range: -6.1559
Max Act: 5.7496. Min Act: -0.1700
Data Index: 1031688 (C4 (Web Text))
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1559. Min Range: -6.1559
Max Act: 5.7496. Min Act: -0.1700
Data Index: 361367 (C4 (Web Text))
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1559. Min Range: -6.1559
Max Act: 5.7184. Min Act: -0.1700
Data Index: 464120 (C4 (Web Text))
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1559. Min Range: -6.1559
Max Act: 5.6871. Min Act: -0.1700
Data Index: 643702 (C4 (Web Text))
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1559. Min Range: -6.1559
Max Act: 5.6559. Min Act: -0.1700
Data Index: 369258 (C4 (Web Text))
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1559. Min Range: -6.1559
Max Act: 5.6559. Min Act: -0.1700
Data Index: 284588 (C4 (Web Text))
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1559. Min Range: -6.1559
Max Act: 5.6559. Min Act: -0.1700
Data Index: 102867 (C4 (Web Text))
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1559. Min Range: -6.1559
Max Act: 5.6246. Min Act: -0.1700
Data Index: 1073285 (C4 (Web Text))
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1559. Min Range: -6.1559
Max Act: 5.6871. Min Act: -0.1700
Data Index: 1088504 (C4 (Web Text))
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1559. Min Range: -6.1559
Max Act: 5.6246. Min Act: -0.1700
Data Index: 75888 (C4 (Web Text))
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1559. Min Range: -6.1559
Max Act: 5.6246. Min Act: -0.1700
Data Index: 259275 (C4 (Web Text))
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1559. Min Range: -6.1559
Max Act: 5.5621. Min Act: -0.1700
Data Index: 631953 (C4 (Web Text))
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #19