Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 648 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2137. Min Range: -7.2137
Max Act: 7.2137. Min Act: -0.1700
Data Index: 1688289 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2137. Min Range: -7.2137
Max Act: 6.9012. Min Act: -0.1700
Data Index: 2315924 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2137. Min Range: -7.2137
Max Act: 6.8699. Min Act: -0.1700
Data Index: 2439451 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2137. Min Range: -7.2137
Max Act: 6.8387. Min Act: -0.1700
Data Index: 1102690 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2137. Min Range: -7.2137
Max Act: 6.8074. Min Act: -0.1700
Data Index: 6590463 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2137. Min Range: -7.2137
Max Act: 6.7762. Min Act: -0.1700
Data Index: 4682666 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2137. Min Range: -7.2137
Max Act: 6.7762. Min Act: -0.1700
Data Index: 2705669 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2137. Min Range: -7.2137
Max Act: 6.7762. Min Act: -0.1700
Data Index: 5513358 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2137. Min Range: -7.2137
Max Act: 6.7449. Min Act: -0.1700
Data Index: 2940674 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2137. Min Range: -7.2137
Max Act: 6.7449. Min Act: -0.1700
Data Index: 3342219 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2137. Min Range: -7.2137
Max Act: 6.7449. Min Act: -0.1700
Data Index: 5606494 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2137. Min Range: -7.2137
Max Act: 6.7137. Min Act: -0.1700
Data Index: 5681114 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2137. Min Range: -7.2137
Max Act: 6.7137. Min Act: -0.1700
Data Index: 7985751 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2137. Min Range: -7.2137
Max Act: 6.7137. Min Act: -0.1700
Data Index: 7750185 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2137. Min Range: -7.2137
Max Act: 6.7137. Min Act: -0.1700
Data Index: 4120503 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2137. Min Range: -7.2137
Max Act: 6.7137. Min Act: -0.1700
Data Index: 5511625 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2137. Min Range: -7.2137
Max Act: 6.7137. Min Act: -0.1700
Data Index: 4700941 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2137. Min Range: -7.2137
Max Act: 6.6512. Min Act: -0.1700
Data Index: 5606495 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2137. Min Range: -7.2137
Max Act: 6.7137. Min Act: -0.1700
Data Index: 4867690 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2137. Min Range: -7.2137
Max Act: 6.6512. Min Act: -0.1700
Data Index: 308272 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #19