Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2948 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7235. Min Range: -7.7235
Max Act: 7.7235. Min Act: -0.1698
Data Index: 8062547 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7235. Min Range: -7.7235
Max Act: 7.4735. Min Act: -0.1700
Data Index: 8062544 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7235. Min Range: -7.7235
Max Act: 7.1923. Min Act: -0.1700
Data Index: 5709187 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7235. Min Range: -7.7235
Max Act: 7.0673. Min Act: -0.1700
Data Index: 2829721 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7235. Min Range: -7.7235
Max Act: 6.9735. Min Act: -0.1700
Data Index: 3305998 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7235. Min Range: -7.7235
Max Act: 6.9735. Min Act: -0.1700
Data Index: 8062550 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7235. Min Range: -7.7235
Max Act: 6.9110. Min Act: -0.1700
Data Index: 7249415 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7235. Min Range: -7.7235
Max Act: 6.8798. Min Act: -0.1696
Data Index: 8333834 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7235. Min Range: -7.7235
Max Act: 6.8798. Min Act: -0.1700
Data Index: 3762429 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7235. Min Range: -7.7235
Max Act: 6.7860. Min Act: -0.1700
Data Index: 5524741 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7235. Min Range: -7.7235
Max Act: 6.7860. Min Act: -0.1700
Data Index: 7454910 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7235. Min Range: -7.7235
Max Act: 6.7548. Min Act: -0.1700
Data Index: 8760532 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7235. Min Range: -7.7235
Max Act: 6.7235. Min Act: -0.1700
Data Index: 5658077 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7235. Min Range: -7.7235
Max Act: 6.6923. Min Act: -0.1700
Data Index: 168683 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7235. Min Range: -7.7235
Max Act: 6.7235. Min Act: -0.1700
Data Index: 4015130 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7235. Min Range: -7.7235
Max Act: 6.7235. Min Act: -0.1700
Data Index: 2780350 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7235. Min Range: -7.7235
Max Act: 6.7235. Min Act: -0.1700
Data Index: 8414359 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7235. Min Range: -7.7235
Max Act: 6.6923. Min Act: -0.1700
Data Index: 8333835 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7235. Min Range: -7.7235
Max Act: 6.6610. Min Act: -0.1700
Data Index: 811000 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7235. Min Range: -7.7235
Max Act: 6.6610. Min Act: -0.1700
Data Index: 8333837 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #19