Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5592 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6052. Min Range: -7.6052
Max Act: 7.6052. Min Act: -0.1700
Data Index: 5418732 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6052. Min Range: -7.6052
Max Act: 7.4802. Min Act: -0.1700
Data Index: 1623732 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6052. Min Range: -7.6052
Max Act: 7.3865. Min Act: -0.1700
Data Index: 3622299 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6052. Min Range: -7.6052
Max Act: 7.1990. Min Act: -0.1700
Data Index: 8827393 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6052. Min Range: -7.6052
Max Act: 7.1990. Min Act: -0.1700
Data Index: 5068250 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6052. Min Range: -7.6052
Max Act: 7.1990. Min Act: -0.1700
Data Index: 7865871 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6052. Min Range: -7.6052
Max Act: 7.1365. Min Act: -0.1700
Data Index: 8225145 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6052. Min Range: -7.6052
Max Act: 7.1052. Min Act: -0.1700
Data Index: 5763100 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6052. Min Range: -7.6052
Max Act: 7.1052. Min Act: -0.1700
Data Index: 8103041 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6052. Min Range: -7.6052
Max Act: 7.1052. Min Act: -0.1700
Data Index: 6668054 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6052. Min Range: -7.6052
Max Act: 7.0427. Min Act: -0.1700
Data Index: 2697448 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6052. Min Range: -7.6052
Max Act: 7.0427. Min Act: -0.1700
Data Index: 4931102 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6052. Min Range: -7.6052
Max Act: 7.0427. Min Act: -0.1700
Data Index: 2055915 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6052. Min Range: -7.6052
Max Act: 7.0115. Min Act: -0.1700
Data Index: 7993376 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6052. Min Range: -7.6052
Max Act: 7.0115. Min Act: -0.1700
Data Index: 2299754 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6052. Min Range: -7.6052
Max Act: 6.9802. Min Act: -0.1700
Data Index: 1217962 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6052. Min Range: -7.6052
Max Act: 6.9802. Min Act: -0.1700
Data Index: 6172294 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6052. Min Range: -7.6052
Max Act: 6.9490. Min Act: -0.1700
Data Index: 3075887 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6052. Min Range: -7.6052
Max Act: 6.9490. Min Act: -0.1700
Data Index: 3050080 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6052. Min Range: -7.6052
Max Act: 6.9490. Min Act: -0.1700
Data Index: 8091145 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #19