Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6392 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8750. Min Range: -6.8750
Max Act: 6.8750. Min Act: -0.1700
Data Index: 7967117 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8750. Min Range: -6.8750
Max Act: 6.8750. Min Act: -0.1700
Data Index: 5700918 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8750. Min Range: -6.8750
Max Act: 6.7500. Min Act: -0.1700
Data Index: 5557796 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8750. Min Range: -6.8750
Max Act: 6.6875. Min Act: -0.1700
Data Index: 8498107 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8750. Min Range: -6.8750
Max Act: 6.5000. Min Act: -0.1700
Data Index: 416837 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8750. Min Range: -6.8750
Max Act: 6.5313. Min Act: -0.1700
Data Index: 6247976 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8750. Min Range: -6.8750
Max Act: 6.4375. Min Act: -0.1700
Data Index: 6392426 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8750. Min Range: -6.8750
Max Act: 6.4063. Min Act: -0.1700
Data Index: 8438901 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8750. Min Range: -6.8750
Max Act: 6.4063. Min Act: -0.1700
Data Index: 5450222 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8750. Min Range: -6.8750
Max Act: 6.3750. Min Act: -0.1700
Data Index: 2997481 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8750. Min Range: -6.8750
Max Act: 6.3750. Min Act: -0.1700
Data Index: 6049089 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8750. Min Range: -6.8750
Max Act: 6.3438. Min Act: -0.1700
Data Index: 6570387 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8750. Min Range: -6.8750
Max Act: 6.3438. Min Act: -0.1700
Data Index: 7797211 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8750. Min Range: -6.8750
Max Act: 6.3438. Min Act: -0.1700
Data Index: 7327172 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8750. Min Range: -6.8750
Max Act: 6.3125. Min Act: -0.1700
Data Index: 2186707 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8750. Min Range: -6.8750
Max Act: 6.3125. Min Act: -0.1700
Data Index: 6993701 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8750. Min Range: -6.8750
Max Act: 6.3125. Min Act: -0.1700
Data Index: 5638259 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8750. Min Range: -6.8750
Max Act: 6.3125. Min Act: -0.1700
Data Index: 1699908 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8750. Min Range: -6.8750
Max Act: 6.2813. Min Act: -0.1700
Data Index: 4894252 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8750. Min Range: -6.8750
Max Act: 6.2813. Min Act: -0.1700
Data Index: 392566 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #19