Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2731 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2309. Min Range: -4.2309
Max Act: 4.2309. Min Act: -0.1700
Data Index: 7297887 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2309. Min Range: -4.2309
Max Act: 4.2309. Min Act: -0.1700
Data Index: 3776371 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2309. Min Range: -4.2309
Max Act: 4.2309. Min Act: -0.1700
Data Index: 3769628 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2309. Min Range: -4.2309
Max Act: 4.2309. Min Act: -0.1700
Data Index: 7936298 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2309. Min Range: -4.2309
Max Act: 4.1996. Min Act: -0.1700
Data Index: 263703 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2309. Min Range: -4.2309
Max Act: 4.1996. Min Act: -0.1700
Data Index: 3769625 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2309. Min Range: -4.2309
Max Act: 4.1996. Min Act: -0.1700
Data Index: 6711942 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2309. Min Range: -4.2309
Max Act: 4.1996. Min Act: -0.1700
Data Index: 3769624 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2309. Min Range: -4.2309
Max Act: 4.1996. Min Act: -0.1700
Data Index: 322476 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2309. Min Range: -4.2309
Max Act: 4.1996. Min Act: -0.1700
Data Index: 3769617 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2309. Min Range: -4.2309
Max Act: 4.1996. Min Act: -0.1700
Data Index: 146931 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2309. Min Range: -4.2309
Max Act: 4.1996. Min Act: -0.1700
Data Index: 266410 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2309. Min Range: -4.2309
Max Act: 4.1996. Min Act: -0.1700
Data Index: 6242015 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2309. Min Range: -4.2309
Max Act: 4.1996. Min Act: -0.1700
Data Index: 3654281 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2309. Min Range: -4.2309
Max Act: 4.1996. Min Act: -0.1700
Data Index: 6146392 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2309. Min Range: -4.2309
Max Act: 4.1996. Min Act: -0.1700
Data Index: 5450891 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2309. Min Range: -4.2309
Max Act: 4.1996. Min Act: -0.1700
Data Index: 4833214 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2309. Min Range: -4.2309
Max Act: 4.1996. Min Act: -0.1700
Data Index: 4564390 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2309. Min Range: -4.2309
Max Act: 4.1996. Min Act: -0.1700
Data Index: 3797792 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2309. Min Range: -4.2309
Max Act: 4.1996. Min Act: -0.1700
Data Index: 3769650 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #19