Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4400 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0393. Min Range: -7.0393
Max Act: 7.0393. Min Act: -0.1700
Data Index: 8700127 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0393. Min Range: -7.0393
Max Act: 7.0081. Min Act: -0.1700
Data Index: 4580204 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0393. Min Range: -7.0393
Max Act: 7.0081. Min Act: -0.1700
Data Index: 2160187 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0393. Min Range: -7.0393
Max Act: 6.9768. Min Act: -0.1700
Data Index: 8124548 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0393. Min Range: -7.0393
Max Act: 6.9456. Min Act: -0.1700
Data Index: 5080179 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0393. Min Range: -7.0393
Max Act: 6.9143. Min Act: -0.1700
Data Index: 7638289 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0393. Min Range: -7.0393
Max Act: 6.8831. Min Act: -0.1700
Data Index: 4254717 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0393. Min Range: -7.0393
Max Act: 6.9143. Min Act: -0.1700
Data Index: 273105 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0393. Min Range: -7.0393
Max Act: 6.8518. Min Act: -0.1700
Data Index: 1460830 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0393. Min Range: -7.0393
Max Act: 6.7893. Min Act: -0.1700
Data Index: 2164991 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0393. Min Range: -7.0393
Max Act: 6.8206. Min Act: -0.1700
Data Index: 277061 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0393. Min Range: -7.0393
Max Act: 6.8206. Min Act: -0.1700
Data Index: 2843042 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0393. Min Range: -7.0393
Max Act: 6.7581. Min Act: -0.1700
Data Index: 1907234 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0393. Min Range: -7.0393
Max Act: 6.7893. Min Act: -0.1700
Data Index: 3940776 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0393. Min Range: -7.0393
Max Act: 6.7581. Min Act: -0.1700
Data Index: 1939571 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0393. Min Range: -7.0393
Max Act: 6.7581. Min Act: -0.1700
Data Index: 3953461 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0393. Min Range: -7.0393
Max Act: 6.6956. Min Act: -0.1700
Data Index: 5404123 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0393. Min Range: -7.0393
Max Act: 6.7268. Min Act: -0.1700
Data Index: 6791008 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0393. Min Range: -7.0393
Max Act: 6.7268. Min Act: -0.1700
Data Index: 1971503 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0393. Min Range: -7.0393
Max Act: 6.7268. Min Act: -0.1700
Data Index: 3011332 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #19