Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2804 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3999. Min Range: -4.3999
Max Act: 4.3999. Min Act: -0.1700
Data Index: 2132684 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3999. Min Range: -4.3999
Max Act: 4.3687. Min Act: -0.1700
Data Index: 6408572 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3999. Min Range: -4.3999
Max Act: 4.3062. Min Act: -0.1700
Data Index: 1054110 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3999. Min Range: -4.3999
Max Act: 4.2124. Min Act: -0.1700
Data Index: 3423969 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3999. Min Range: -4.3999
Max Act: 4.1499. Min Act: -0.1700
Data Index: 4493446 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3999. Min Range: -4.3999
Max Act: 4.1499. Min Act: -0.1700
Data Index: 5208317 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3999. Min Range: -4.3999
Max Act: 4.1499. Min Act: -0.1700
Data Index: 3921777 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3999. Min Range: -4.3999
Max Act: 4.1499. Min Act: -0.1700
Data Index: 2224646 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3999. Min Range: -4.3999
Max Act: 4.1187. Min Act: -0.1700
Data Index: 2333164 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3999. Min Range: -4.3999
Max Act: 4.1187. Min Act: -0.1700
Data Index: 6491487 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3999. Min Range: -4.3999
Max Act: 4.1187. Min Act: -0.1700
Data Index: 8334416 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3999. Min Range: -4.3999
Max Act: 4.1187. Min Act: -0.1700
Data Index: 5168941 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3999. Min Range: -4.3999
Max Act: 4.0874. Min Act: -0.1700
Data Index: 3247698 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3999. Min Range: -4.3999
Max Act: 4.0874. Min Act: -0.1700
Data Index: 6955740 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3999. Min Range: -4.3999
Max Act: 4.0874. Min Act: -0.1700
Data Index: 233068 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3999. Min Range: -4.3999
Max Act: 4.0874. Min Act: -0.1700
Data Index: 6774564 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3999. Min Range: -4.3999
Max Act: 4.0874. Min Act: -0.1700
Data Index: 6219415 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3999. Min Range: -4.3999
Max Act: 4.0561. Min Act: -0.1700
Data Index: 1871234 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3999. Min Range: -4.3999
Max Act: 4.0561. Min Act: -0.1700
Data Index: 5329281 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3999. Min Range: -4.3999
Max Act: 4.0561. Min Act: -0.1700
Data Index: 5537300 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #19