Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 724 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.1923. Min Range: -6.1923
Max Act: 6.1923. Min Act: -0.1700
Data Index: 2915377 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1923. Min Range: -6.1923
Max Act: 6.0048. Min Act: -0.1700
Data Index: 1684385 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1923. Min Range: -6.1923
Max Act: 5.9423. Min Act: -0.1700
Data Index: 3355323 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1923. Min Range: -6.1923
Max Act: 5.8485. Min Act: -0.1700
Data Index: 4554537 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1923. Min Range: -6.1923
Max Act: 5.7860. Min Act: -0.1700
Data Index: 6661908 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1923. Min Range: -6.1923
Max Act: 5.7860. Min Act: -0.1700
Data Index: 6978448 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1923. Min Range: -6.1923
Max Act: 5.7548. Min Act: -0.1700
Data Index: 8729538 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1923. Min Range: -6.1923
Max Act: 5.6923. Min Act: -0.1700
Data Index: 532773 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1923. Min Range: -6.1923
Max Act: 5.6923. Min Act: -0.1700
Data Index: 5714849 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1923. Min Range: -6.1923
Max Act: 5.6923. Min Act: -0.1700
Data Index: 2392817 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1923. Min Range: -6.1923
Max Act: 5.6610. Min Act: -0.1700
Data Index: 1395376 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1923. Min Range: -6.1923
Max Act: 5.6298. Min Act: -0.1700
Data Index: 471809 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1923. Min Range: -6.1923
Max Act: 5.6298. Min Act: -0.1700
Data Index: 1669569 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1923. Min Range: -6.1923
Max Act: 5.5985. Min Act: -0.1700
Data Index: 2512165 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1923. Min Range: -6.1923
Max Act: 5.5985. Min Act: -0.1700
Data Index: 6424429 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1923. Min Range: -6.1923
Max Act: 5.5673. Min Act: -0.1700
Data Index: 5532065 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1923. Min Range: -6.1923
Max Act: 5.5673. Min Act: -0.1700
Data Index: 8416678 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1923. Min Range: -6.1923
Max Act: 5.5360. Min Act: -0.1700
Data Index: 6917754 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1923. Min Range: -6.1923
Max Act: 5.5673. Min Act: -0.1700
Data Index: 5029689 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1923. Min Range: -6.1923
Max Act: 5.5048. Min Act: -0.1700
Data Index: 5302964 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #19