Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3509 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.0063. Min Range: -4.0063
Max Act: 4.0063. Min Act: -0.1700
Data Index: 5864155 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0063. Min Range: -4.0063
Max Act: 4.0063. Min Act: -0.1700
Data Index: 5094783 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0063. Min Range: -4.0063
Max Act: 4.0063. Min Act: -0.1700
Data Index: 529801 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0063. Min Range: -4.0063
Max Act: 3.9750. Min Act: -0.1700
Data Index: 1421099 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0063. Min Range: -4.0063
Max Act: 3.9437. Min Act: -0.1700
Data Index: 5999761 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0063. Min Range: -4.0063
Max Act: 3.8812. Min Act: -0.1700
Data Index: 1524286 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0063. Min Range: -4.0063
Max Act: 3.9125. Min Act: -0.1700
Data Index: 5258905 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0063. Min Range: -4.0063
Max Act: 3.9125. Min Act: -0.1700
Data Index: 2548018 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0063. Min Range: -4.0063
Max Act: 3.9437. Min Act: -0.1700
Data Index: 686350 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0063. Min Range: -4.0063
Max Act: 3.8812. Min Act: -0.1700
Data Index: 6778629 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0063. Min Range: -4.0063
Max Act: 3.9437. Min Act: -0.1700
Data Index: 3051884 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0063. Min Range: -4.0063
Max Act: 3.8812. Min Act: -0.1700
Data Index: 3400427 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0063. Min Range: -4.0063
Max Act: 3.8812. Min Act: -0.1700
Data Index: 6211491 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0063. Min Range: -4.0063
Max Act: 3.8812. Min Act: -0.1700
Data Index: 8588249 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0063. Min Range: -4.0063
Max Act: 3.8812. Min Act: -0.1700
Data Index: 4203344 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0063. Min Range: -4.0063
Max Act: 3.8812. Min Act: -0.1700
Data Index: 1170418 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0063. Min Range: -4.0063
Max Act: 3.8499. Min Act: -0.1700
Data Index: 3279644 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0063. Min Range: -4.0063
Max Act: 3.8187. Min Act: -0.1700
Data Index: 4129233 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0063. Min Range: -4.0063
Max Act: 3.8499. Min Act: -0.1700
Data Index: 2388592 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0063. Min Range: -4.0063
Max Act: 3.8187. Min Act: -0.1700
Data Index: 2688049 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #19