Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2590 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9063. Min Range: -8.9063
Max Act: 8.9063. Min Act: -0.1700
Data Index: 6803261 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9063. Min Range: -8.9063
Max Act: 8.8438. Min Act: -0.1700
Data Index: 3767176 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9063. Min Range: -8.9063
Max Act: 8.6563. Min Act: -0.1700
Data Index: 8729274 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9063. Min Range: -8.9063
Max Act: 8.5938. Min Act: -0.1700
Data Index: 386133 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9063. Min Range: -8.9063
Max Act: 8.5938. Min Act: -0.1700
Data Index: 5307151 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9063. Min Range: -8.9063
Max Act: 8.5313. Min Act: -0.1700
Data Index: 4874318 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9063. Min Range: -8.9063
Max Act: 8.4688. Min Act: -0.1700
Data Index: 4247863 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9063. Min Range: -8.9063
Max Act: 8.4688. Min Act: -0.1700
Data Index: 7600883 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9063. Min Range: -8.9063
Max Act: 8.4063. Min Act: -0.1700
Data Index: 2601081 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9063. Min Range: -8.9063
Max Act: 8.4063. Min Act: -0.1700
Data Index: 4153007 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9063. Min Range: -8.9063
Max Act: 8.3438. Min Act: -0.1700
Data Index: 3775470 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9063. Min Range: -8.9063
Max Act: 8.3438. Min Act: -0.1700
Data Index: 2583393 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9063. Min Range: -8.9063
Max Act: 8.3438. Min Act: -0.1700
Data Index: 6903883 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9063. Min Range: -8.9063
Max Act: 8.3438. Min Act: -0.1700
Data Index: 3383939 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9063. Min Range: -8.9063
Max Act: 8.2813. Min Act: -0.1700
Data Index: 4651377 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9063. Min Range: -8.9063
Max Act: 8.2813. Min Act: -0.1700
Data Index: 4357412 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9063. Min Range: -8.9063
Max Act: 8.2813. Min Act: -0.1700
Data Index: 4052286 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9063. Min Range: -8.9063
Max Act: 8.2813. Min Act: -0.1700
Data Index: 1140772 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9063. Min Range: -8.9063
Max Act: 8.2188. Min Act: -0.1700
Data Index: 264360 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9063. Min Range: -8.9063
Max Act: 8.2188. Min Act: -0.1700
Data Index: 7736570 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #19