Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3589 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5159. Min Range: -6.5159
Max Act: 6.5159. Min Act: -0.1700
Data Index: 4800105 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5159. Min Range: -6.5159
Max Act: 6.2034. Min Act: -0.1700
Data Index: 7777697 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5159. Min Range: -6.5159
Max Act: 6.1721. Min Act: -0.1700
Data Index: 1297622 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5159. Min Range: -6.5159
Max Act: 6.1721. Min Act: -0.1700
Data Index: 1166515 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5159. Min Range: -6.5159
Max Act: 6.1721. Min Act: -0.1700
Data Index: 5566179 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5159. Min Range: -6.5159
Max Act: 6.0784. Min Act: -0.1700
Data Index: 6357882 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5159. Min Range: -6.5159
Max Act: 6.0784. Min Act: -0.1700
Data Index: 4212406 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5159. Min Range: -6.5159
Max Act: 6.0784. Min Act: -0.1700
Data Index: 6089219 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5159. Min Range: -6.5159
Max Act: 6.0159. Min Act: -0.1700
Data Index: 5373358 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5159. Min Range: -6.5159
Max Act: 6.0159. Min Act: -0.1700
Data Index: 5851756 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5159. Min Range: -6.5159
Max Act: 5.9221. Min Act: -0.1700
Data Index: 8336668 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5159. Min Range: -6.5159
Max Act: 5.8909. Min Act: -0.1700
Data Index: 1471688 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5159. Min Range: -6.5159
Max Act: 5.8909. Min Act: -0.1700
Data Index: 6593759 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5159. Min Range: -6.5159
Max Act: 5.8909. Min Act: -0.1700
Data Index: 8615077 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5159. Min Range: -6.5159
Max Act: 5.8909. Min Act: -0.1700
Data Index: 4645985 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5159. Min Range: -6.5159
Max Act: 5.7971. Min Act: -0.1700
Data Index: 3582437 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5159. Min Range: -6.5159
Max Act: 5.8284. Min Act: -0.1700
Data Index: 4952329 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5159. Min Range: -6.5159
Max Act: 5.7971. Min Act: -0.1700
Data Index: 2133513 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5159. Min Range: -6.5159
Max Act: 5.7971. Min Act: -0.1700
Data Index: 6937708 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5159. Min Range: -6.5159
Max Act: 5.7971. Min Act: -0.1700
Data Index: 5446468 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #19