Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4277 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6012. Min Range: -5.6012
Max Act: 5.6012. Min Act: -0.1700
Data Index: 575984 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6012. Min Range: -5.6012
Max Act: 5.6012. Min Act: -0.1700
Data Index: 2892241 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6012. Min Range: -5.6012
Max Act: 5.5699. Min Act: -0.1700
Data Index: 7108504 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6012. Min Range: -5.6012
Max Act: 5.6012. Min Act: -0.1700
Data Index: 8641407 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6012. Min Range: -5.6012
Max Act: 5.5699. Min Act: -0.1700
Data Index: 7600688 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6012. Min Range: -5.6012
Max Act: 5.5387. Min Act: -0.1700
Data Index: 5949273 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6012. Min Range: -5.6012
Max Act: 5.5387. Min Act: -0.1700
Data Index: 4895942 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6012. Min Range: -5.6012
Max Act: 5.5387. Min Act: -0.1700
Data Index: 1561914 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6012. Min Range: -5.6012
Max Act: 5.5387. Min Act: -0.1700
Data Index: 3893244 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6012. Min Range: -5.6012
Max Act: 5.5387. Min Act: -0.1700
Data Index: 977415 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6012. Min Range: -5.6012
Max Act: 5.5074. Min Act: -0.1700
Data Index: 2861947 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6012. Min Range: -5.6012
Max Act: 5.5074. Min Act: -0.1700
Data Index: 5685991 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6012. Min Range: -5.6012
Max Act: 5.5074. Min Act: -0.1698
Data Index: 7768362 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6012. Min Range: -5.6012
Max Act: 5.5074. Min Act: -0.1700
Data Index: 8127671 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6012. Min Range: -5.6012
Max Act: 5.5074. Min Act: -0.1700
Data Index: 8412403 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6012. Min Range: -5.6012
Max Act: 5.5074. Min Act: -0.1696
Data Index: 8272164 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6012. Min Range: -5.6012
Max Act: 5.5074. Min Act: -0.1699
Data Index: 8244868 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6012. Min Range: -5.6012
Max Act: 5.4762. Min Act: -0.1700
Data Index: 889265 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6012. Min Range: -5.6012
Max Act: 5.4762. Min Act: -0.1700
Data Index: 5891076 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6012. Min Range: -5.6012
Max Act: 5.4762. Min Act: -0.1700
Data Index: 5008312 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #19