Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 647 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9909. Min Range: -5.9909
Max Act: 5.9909. Min Act: -0.1700
Data Index: 6114544 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9909. Min Range: -5.9909
Max Act: 5.9909. Min Act: -0.1700
Data Index: 5100503 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9909. Min Range: -5.9909
Max Act: 5.9597. Min Act: -0.1700
Data Index: 2505031 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9909. Min Range: -5.9909
Max Act: 5.8347. Min Act: -0.1700
Data Index: 3274162 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9909. Min Range: -5.9909
Max Act: 5.8034. Min Act: -0.1700
Data Index: 662060 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9909. Min Range: -5.9909
Max Act: 5.8034. Min Act: -0.1700
Data Index: 1707297 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9909. Min Range: -5.9909
Max Act: 5.8034. Min Act: -0.1700
Data Index: 1458728 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9909. Min Range: -5.9909
Max Act: 5.8034. Min Act: -0.1700
Data Index: 5899836 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9909. Min Range: -5.9909
Max Act: 5.7722. Min Act: -0.1700
Data Index: 3917176 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9909. Min Range: -5.9909
Max Act: 5.7722. Min Act: -0.1700
Data Index: 1696169 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9909. Min Range: -5.9909
Max Act: 5.7409. Min Act: -0.1700
Data Index: 4624458 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9909. Min Range: -5.9909
Max Act: 5.7097. Min Act: -0.1700
Data Index: 693392 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9909. Min Range: -5.9909
Max Act: 5.7097. Min Act: -0.1700
Data Index: 2112687 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9909. Min Range: -5.9909
Max Act: 5.7097. Min Act: -0.1700
Data Index: 8784593 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9909. Min Range: -5.9909
Max Act: 5.6784. Min Act: -0.1700
Data Index: 5608812 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9909. Min Range: -5.9909
Max Act: 5.6784. Min Act: -0.1700
Data Index: 6246021 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9909. Min Range: -5.9909
Max Act: 5.6784. Min Act: -0.1700
Data Index: 5100459 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9909. Min Range: -5.9909
Max Act: 5.6784. Min Act: -0.1700
Data Index: 7480898 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9909. Min Range: -5.9909
Max Act: 5.6784. Min Act: -0.1700
Data Index: 8276597 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9909. Min Range: -5.9909
Max Act: 5.7097. Min Act: -0.1700
Data Index: 2902937 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #19