Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 625 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7923. Min Range: -6.7923
Max Act: 6.7923. Min Act: -0.1700
Data Index: 1190086 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7923. Min Range: -6.7923
Max Act: 6.6048. Min Act: -0.1700
Data Index: 6980175 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7923. Min Range: -6.7923
Max Act: 6.5735. Min Act: -0.1700
Data Index: 7734038 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7923. Min Range: -6.7923
Max Act: 6.3235. Min Act: -0.1700
Data Index: 4860570 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7923. Min Range: -6.7923
Max Act: 6.2298. Min Act: -0.1700
Data Index: 1093361 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7923. Min Range: -6.7923
Max Act: 6.1985. Min Act: -0.1700
Data Index: 7667537 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7923. Min Range: -6.7923
Max Act: 6.1673. Min Act: -0.1700
Data Index: 3803849 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7923. Min Range: -6.7923
Max Act: 6.1360. Min Act: -0.1700
Data Index: 4501853 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7923. Min Range: -6.7923
Max Act: 6.0735. Min Act: -0.1700
Data Index: 1624291 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7923. Min Range: -6.7923
Max Act: 6.0423. Min Act: -0.1700
Data Index: 2491990 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7923. Min Range: -6.7923
Max Act: 6.0110. Min Act: -0.1700
Data Index: 2750093 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7923. Min Range: -6.7923
Max Act: 6.0423. Min Act: -0.1700
Data Index: 3678913 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7923. Min Range: -6.7923
Max Act: 6.0423. Min Act: -0.1700
Data Index: 2009134 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7923. Min Range: -6.7923
Max Act: 5.9798. Min Act: -0.1700
Data Index: 8156896 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7923. Min Range: -6.7923
Max Act: 5.9173. Min Act: -0.1700
Data Index: 2568340 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7923. Min Range: -6.7923
Max Act: 5.8860. Min Act: -0.1700
Data Index: 1899002 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7923. Min Range: -6.7923
Max Act: 5.8860. Min Act: -0.1700
Data Index: 4417662 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7923. Min Range: -6.7923
Max Act: 5.8860. Min Act: -0.1700
Data Index: 7968076 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7923. Min Range: -6.7923
Max Act: 5.8860. Min Act: -0.1700
Data Index: 3874541 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7923. Min Range: -6.7923
Max Act: 5.8548. Min Act: -0.1700
Data Index: 5691455 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #19