Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5082 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5093. Min Range: -6.5093
Max Act: 6.5093. Min Act: -0.1700
Data Index: 3781116 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5093. Min Range: -6.5093
Max Act: 6.4155. Min Act: -0.1700
Data Index: 4867210 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5093. Min Range: -6.5093
Max Act: 6.3843. Min Act: -0.1700
Data Index: 4079269 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5093. Min Range: -6.5093
Max Act: 6.3843. Min Act: -0.1700
Data Index: 1201399 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5093. Min Range: -6.5093
Max Act: 6.1343. Min Act: -0.1700
Data Index: 3632576 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5093. Min Range: -6.5093
Max Act: 6.1030. Min Act: -0.1700
Data Index: 1085837 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5093. Min Range: -6.5093
Max Act: 6.0093. Min Act: -0.1700
Data Index: 8645082 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5093. Min Range: -6.5093
Max Act: 6.0093. Min Act: -0.1700
Data Index: 1843974 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5093. Min Range: -6.5093
Max Act: 5.9780. Min Act: -0.1700
Data Index: 7850986 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5093. Min Range: -6.5093
Max Act: 5.9780. Min Act: -0.1700
Data Index: 3721104 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5093. Min Range: -6.5093
Max Act: 6.0093. Min Act: -0.1700
Data Index: 2671900 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5093. Min Range: -6.5093
Max Act: 6.0093. Min Act: -0.1700
Data Index: 4560895 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5093. Min Range: -6.5093
Max Act: 5.9780. Min Act: -0.1700
Data Index: 179794 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5093. Min Range: -6.5093
Max Act: 5.9468. Min Act: -0.1700
Data Index: 1109505 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5093. Min Range: -6.5093
Max Act: 5.9468. Min Act: -0.1700
Data Index: 612192 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5093. Min Range: -6.5093
Max Act: 5.9468. Min Act: -0.1700
Data Index: 5137479 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5093. Min Range: -6.5093
Max Act: 5.9468. Min Act: -0.1700
Data Index: 8690458 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5093. Min Range: -6.5093
Max Act: 5.9468. Min Act: -0.1700
Data Index: 401476 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5093. Min Range: -6.5093
Max Act: 5.9155. Min Act: -0.1700
Data Index: 128851 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5093. Min Range: -6.5093
Max Act: 5.9155. Min Act: -0.1700
Data Index: 4301850 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #19