Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2853 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0115. Min Range: -6.0115
Max Act: 6.0115. Min Act: -0.1700
Data Index: 2565644 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0115. Min Range: -6.0115
Max Act: 6.0115. Min Act: -0.1700
Data Index: 2463251 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0115. Min Range: -6.0115
Max Act: 5.9490. Min Act: -0.1700
Data Index: 2491938 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0115. Min Range: -6.0115
Max Act: 5.8865. Min Act: -0.1700
Data Index: 6920284 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0115. Min Range: -6.0115
Max Act: 5.8865. Min Act: -0.1700
Data Index: 802572 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0115. Min Range: -6.0115
Max Act: 5.8552. Min Act: -0.1700
Data Index: 6947824 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0115. Min Range: -6.0115
Max Act: 5.8240. Min Act: -0.1700
Data Index: 3606309 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0115. Min Range: -6.0115
Max Act: 5.8240. Min Act: -0.1700
Data Index: 6579946 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0115. Min Range: -6.0115
Max Act: 5.7302. Min Act: -0.1700
Data Index: 4538485 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0115. Min Range: -6.0115
Max Act: 5.7302. Min Act: -0.1700
Data Index: 6451438 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0115. Min Range: -6.0115
Max Act: 5.6677. Min Act: -0.1700
Data Index: 5790132 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0115. Min Range: -6.0115
Max Act: 5.6677. Min Act: -0.1700
Data Index: 7597470 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0115. Min Range: -6.0115
Max Act: 5.6052. Min Act: -0.1700
Data Index: 5981563 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0115. Min Range: -6.0115
Max Act: 5.6052. Min Act: -0.1700
Data Index: 662150 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0115. Min Range: -6.0115
Max Act: 5.5740. Min Act: -0.1700
Data Index: 6214241 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0115. Min Range: -6.0115
Max Act: 5.5740. Min Act: -0.1700
Data Index: 2894939 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0115. Min Range: -6.0115
Max Act: 5.6052. Min Act: -0.1700
Data Index: 6147242 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0115. Min Range: -6.0115
Max Act: 5.5740. Min Act: -0.1700
Data Index: 6326057 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0115. Min Range: -6.0115
Max Act: 5.5427. Min Act: -0.1700
Data Index: 4181630 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0115. Min Range: -6.0115
Max Act: 5.5427. Min Act: -0.1700
Data Index: 5597915 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #19