Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5464 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5212. Min Range: -5.5212
Max Act: 5.5212. Min Act: -0.1700
Data Index: 5567042 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5212. Min Range: -5.5212
Max Act: 5.4587. Min Act: -0.1700
Data Index: 1137722 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5212. Min Range: -5.5212
Max Act: 5.2712. Min Act: -0.1700
Data Index: 607774 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5212. Min Range: -5.5212
Max Act: 5.2400. Min Act: -0.1700
Data Index: 8601284 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5212. Min Range: -5.5212
Max Act: 5.1775. Min Act: -0.1700
Data Index: 4340057 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5212. Min Range: -5.5212
Max Act: 5.2087. Min Act: -0.1700
Data Index: 2563271 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5212. Min Range: -5.5212
Max Act: 5.1775. Min Act: -0.1700
Data Index: 7437596 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5212. Min Range: -5.5212
Max Act: 5.1775. Min Act: -0.1700
Data Index: 2074753 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5212. Min Range: -5.5212
Max Act: 5.1462. Min Act: -0.1700
Data Index: 4709403 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5212. Min Range: -5.5212
Max Act: 5.1462. Min Act: -0.1700
Data Index: 4247067 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5212. Min Range: -5.5212
Max Act: 5.1150. Min Act: -0.1700
Data Index: 5624790 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5212. Min Range: -5.5212
Max Act: 5.1150. Min Act: -0.1700
Data Index: 1332992 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5212. Min Range: -5.5212
Max Act: 5.0837. Min Act: -0.1700
Data Index: 8437011 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5212. Min Range: -5.5212
Max Act: 5.0837. Min Act: -0.1700
Data Index: 7575431 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5212. Min Range: -5.5212
Max Act: 5.0525. Min Act: -0.1700
Data Index: 5498726 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5212. Min Range: -5.5212
Max Act: 5.0525. Min Act: -0.1700
Data Index: 2688855 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5212. Min Range: -5.5212
Max Act: 5.0525. Min Act: -0.1700
Data Index: 3772411 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5212. Min Range: -5.5212
Max Act: 5.0837. Min Act: -0.1700
Data Index: 7575432 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5212. Min Range: -5.5212
Max Act: 5.0212. Min Act: -0.1700
Data Index: 3301625 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5212. Min Range: -5.5212
Max Act: 5.0212. Min Act: -0.1700
Data Index: 5102275 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #19