Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 15 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4807. Min Range: -6.4807
Max Act: 6.4807. Min Act: -0.1700
Data Index: 7469522 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4807. Min Range: -6.4807
Max Act: 6.3557. Min Act: -0.1700
Data Index: 5481388 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4807. Min Range: -6.4807
Max Act: 6.0744. Min Act: -0.1700
Data Index: 5440854 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4807. Min Range: -6.4807
Max Act: 6.1057. Min Act: -0.1700
Data Index: 5665697 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4807. Min Range: -6.4807
Max Act: 6.0119. Min Act: -0.1700
Data Index: 7543312 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4807. Min Range: -6.4807
Max Act: 6.0119. Min Act: -0.1700
Data Index: 5527484 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4807. Min Range: -6.4807
Max Act: 6.0432. Min Act: -0.1700
Data Index: 4895815 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4807. Min Range: -6.4807
Max Act: 6.0119. Min Act: -0.1700
Data Index: 1520992 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4807. Min Range: -6.4807
Max Act: 5.9494. Min Act: -0.1700
Data Index: 3964563 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4807. Min Range: -6.4807
Max Act: 5.9494. Min Act: -0.1700
Data Index: 3619582 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4807. Min Range: -6.4807
Max Act: 5.9494. Min Act: -0.1700
Data Index: 3286932 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4807. Min Range: -6.4807
Max Act: 5.9182. Min Act: -0.1700
Data Index: 5320184 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4807. Min Range: -6.4807
Max Act: 5.8869. Min Act: -0.1700
Data Index: 7302868 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4807. Min Range: -6.4807
Max Act: 5.8869. Min Act: -0.1700
Data Index: 701532 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4807. Min Range: -6.4807
Max Act: 5.8869. Min Act: -0.1700
Data Index: 8404158 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4807. Min Range: -6.4807
Max Act: 5.8869. Min Act: -0.1700
Data Index: 1876147 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4807. Min Range: -6.4807
Max Act: 5.8244. Min Act: -0.1700
Data Index: 7209185 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4807. Min Range: -6.4807
Max Act: 5.8557. Min Act: -0.1700
Data Index: 2464438 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4807. Min Range: -6.4807
Max Act: 5.8557. Min Act: -0.1700
Data Index: 5547325 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4807. Min Range: -6.4807
Max Act: 5.8869. Min Act: -0.1700
Data Index: 7686494 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #19