Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4521 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8534. Min Range: -5.8534
Max Act: 5.8534. Min Act: -0.1700
Data Index: 1759544 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8534. Min Range: -5.8534
Max Act: 5.8534. Min Act: -0.1700
Data Index: 8104142 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8534. Min Range: -5.8534
Max Act: 5.8221. Min Act: -0.1700
Data Index: 6529004 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8534. Min Range: -5.8534
Max Act: 5.7909. Min Act: -0.1700
Data Index: 7003982 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8534. Min Range: -5.8534
Max Act: 5.7909. Min Act: -0.1700
Data Index: 2648011 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8534. Min Range: -5.8534
Max Act: 5.7909. Min Act: -0.1700
Data Index: 454241 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8534. Min Range: -5.8534
Max Act: 5.7909. Min Act: -0.1700
Data Index: 213800 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8534. Min Range: -5.8534
Max Act: 5.7596. Min Act: -0.1700
Data Index: 1840175 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8534. Min Range: -5.8534
Max Act: 5.7596. Min Act: -0.1700
Data Index: 4716921 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8534. Min Range: -5.8534
Max Act: 5.7596. Min Act: -0.1700
Data Index: 790501 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8534. Min Range: -5.8534
Max Act: 5.7284. Min Act: -0.1700
Data Index: 6752905 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8534. Min Range: -5.8534
Max Act: 5.7596. Min Act: -0.1700
Data Index: 3535848 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8534. Min Range: -5.8534
Max Act: 5.7596. Min Act: -0.1700
Data Index: 35226 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8534. Min Range: -5.8534
Max Act: 5.6971. Min Act: -0.1700
Data Index: 2501821 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8534. Min Range: -5.8534
Max Act: 5.7284. Min Act: -0.1700
Data Index: 672798 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8534. Min Range: -5.8534
Max Act: 5.7284. Min Act: -0.1700
Data Index: 6830105 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8534. Min Range: -5.8534
Max Act: 5.7284. Min Act: -0.1700
Data Index: 6375116 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8534. Min Range: -5.8534
Max Act: 5.7284. Min Act: -0.1700
Data Index: 6375106 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8534. Min Range: -5.8534
Max Act: 5.6971. Min Act: -0.1700
Data Index: 1121938 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8534. Min Range: -5.8534
Max Act: 5.7284. Min Act: -0.1700
Data Index: 5935271 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #19