Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1837 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1923. Min Range: -7.1923
Max Act: 7.1923. Min Act: -0.1700
Data Index: 366398 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1923. Min Range: -7.1923
Max Act: 7.1611. Min Act: -0.1700
Data Index: 3185803 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1923. Min Range: -7.1923
Max Act: 7.1298. Min Act: -0.1700
Data Index: 7888174 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1923. Min Range: -7.1923
Max Act: 7.1298. Min Act: -0.1700
Data Index: 3815358 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1923. Min Range: -7.1923
Max Act: 7.0673. Min Act: -0.1700
Data Index: 2101464 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1923. Min Range: -7.1923
Max Act: 7.0361. Min Act: -0.1700
Data Index: 7104251 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1923. Min Range: -7.1923
Max Act: 7.0361. Min Act: -0.1700
Data Index: 691527 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1923. Min Range: -7.1923
Max Act: 7.0361. Min Act: -0.1700
Data Index: 5302518 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1923. Min Range: -7.1923
Max Act: 7.0361. Min Act: -0.1700
Data Index: 216750 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1923. Min Range: -7.1923
Max Act: 7.0673. Min Act: -0.1700
Data Index: 8646332 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1923. Min Range: -7.1923
Max Act: 6.9423. Min Act: -0.1700
Data Index: 5475540 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1923. Min Range: -7.1923
Max Act: 6.9736. Min Act: -0.1700
Data Index: 4260659 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1923. Min Range: -7.1923
Max Act: 6.9736. Min Act: -0.1700
Data Index: 5302517 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1923. Min Range: -7.1923
Max Act: 6.9736. Min Act: -0.1700
Data Index: 1245433 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1923. Min Range: -7.1923
Max Act: 6.9423. Min Act: -0.1700
Data Index: 6285308 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1923. Min Range: -7.1923
Max Act: 7.0048. Min Act: -0.1700
Data Index: 4188251 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1923. Min Range: -7.1923
Max Act: 6.9736. Min Act: -0.1700
Data Index: 5756993 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1923. Min Range: -7.1923
Max Act: 6.9423. Min Act: -0.1700
Data Index: 3367635 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1923. Min Range: -7.1923
Max Act: 6.9736. Min Act: -0.1700
Data Index: 6907481 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1923. Min Range: -7.1923
Max Act: 6.9423. Min Act: -0.1700
Data Index: 5322002 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #19