Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3353 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8063. Min Range: -4.8063
Max Act: 4.8063. Min Act: -0.1700
Data Index: 8094299 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8063. Min Range: -4.8063
Max Act: 4.8063. Min Act: -0.1700
Data Index: 5712479 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8063. Min Range: -4.8063
Max Act: 4.8063. Min Act: -0.1700
Data Index: 2414174 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8063. Min Range: -4.8063
Max Act: 4.6813. Min Act: -0.1700
Data Index: 8684539 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8063. Min Range: -4.8063
Max Act: 4.6813. Min Act: -0.1700
Data Index: 3640803 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8063. Min Range: -4.8063
Max Act: 4.6501. Min Act: -0.1700
Data Index: 7173069 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8063. Min Range: -4.8063
Max Act: 4.6188. Min Act: -0.1700
Data Index: 1748083 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8063. Min Range: -4.8063
Max Act: 4.5876. Min Act: -0.1700
Data Index: 4213810 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8063. Min Range: -4.8063
Max Act: 4.5876. Min Act: -0.1700
Data Index: 2768449 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8063. Min Range: -4.8063
Max Act: 4.5251. Min Act: -0.1700
Data Index: 4252270 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8063. Min Range: -4.8063
Max Act: 4.5251. Min Act: -0.1700
Data Index: 6022712 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8063. Min Range: -4.8063
Max Act: 4.5251. Min Act: -0.1700
Data Index: 8396019 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8063. Min Range: -4.8063
Max Act: 4.5251. Min Act: -0.1700
Data Index: 703847 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8063. Min Range: -4.8063
Max Act: 4.4938. Min Act: -0.1700
Data Index: 2879350 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8063. Min Range: -4.8063
Max Act: 4.4938. Min Act: -0.1700
Data Index: 355068 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8063. Min Range: -4.8063
Max Act: 4.5251. Min Act: -0.1700
Data Index: 8152583 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8063. Min Range: -4.8063
Max Act: 4.4938. Min Act: -0.1700
Data Index: 6548598 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8063. Min Range: -4.8063
Max Act: 4.4626. Min Act: -0.1700
Data Index: 6916560 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8063. Min Range: -4.8063
Max Act: 4.4626. Min Act: -0.1700
Data Index: 7336630 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8063. Min Range: -4.8063
Max Act: 4.4626. Min Act: -0.1700
Data Index: 2827188 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #19