Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3064 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.6093. Min Range: -5.6093
Max Act: 5.6093. Min Act: -0.1700
Data Index: 3740641 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6093. Min Range: -5.6093
Max Act: 5.4530. Min Act: -0.1700
Data Index: 8011877 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6093. Min Range: -5.6093
Max Act: 5.2655. Min Act: -0.1700
Data Index: 8413734 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6093. Min Range: -5.6093
Max Act: 5.2343. Min Act: -0.1700
Data Index: 5464594 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6093. Min Range: -5.6093
Max Act: 5.2030. Min Act: -0.1700
Data Index: 3019760 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6093. Min Range: -5.6093
Max Act: 5.1718. Min Act: -0.1700
Data Index: 4704115 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6093. Min Range: -5.6093
Max Act: 5.1718. Min Act: -0.1700
Data Index: 678854 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6093. Min Range: -5.6093
Max Act: 5.1718. Min Act: -0.1700
Data Index: 7150491 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6093. Min Range: -5.6093
Max Act: 5.1718. Min Act: -0.1700
Data Index: 8194891 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6093. Min Range: -5.6093
Max Act: 5.1718. Min Act: -0.1700
Data Index: 5432512 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6093. Min Range: -5.6093
Max Act: 5.1718. Min Act: -0.1700
Data Index: 4462973 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6093. Min Range: -5.6093
Max Act: 5.1093. Min Act: -0.1700
Data Index: 8251608 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6093. Min Range: -5.6093
Max Act: 5.1405. Min Act: -0.1700
Data Index: 2291186 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6093. Min Range: -5.6093
Max Act: 5.1405. Min Act: -0.1700
Data Index: 7271374 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6093. Min Range: -5.6093
Max Act: 5.1405. Min Act: -0.1700
Data Index: 5267241 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6093. Min Range: -5.6093
Max Act: 5.1405. Min Act: -0.1700
Data Index: 5420187 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6093. Min Range: -5.6093
Max Act: 5.1405. Min Act: -0.1700
Data Index: 3145368 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6093. Min Range: -5.6093
Max Act: 5.1405. Min Act: -0.1700
Data Index: 7771292 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6093. Min Range: -5.6093
Max Act: 5.1093. Min Act: -0.1700
Data Index: 922575 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6093. Min Range: -5.6093
Max Act: 5.1093. Min Act: -0.1700
Data Index: 6507787 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #19