Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3347 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0620. Min Range: -5.0620
Max Act: 5.0620. Min Act: -0.1700
Data Index: 7795843 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0620. Min Range: -5.0620
Max Act: 4.8745. Min Act: -0.1700
Data Index: 6983941 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0620. Min Range: -5.0620
Max Act: 4.8120. Min Act: -0.1700
Data Index: 1282603 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0620. Min Range: -5.0620
Max Act: 4.8745. Min Act: -0.1700
Data Index: 6018815 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0620. Min Range: -5.0620
Max Act: 4.7808. Min Act: -0.1700
Data Index: 6643158 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0620. Min Range: -5.0620
Max Act: 4.8120. Min Act: -0.1700
Data Index: 5726372 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0620. Min Range: -5.0620
Max Act: 4.8120. Min Act: -0.1700
Data Index: 8612475 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0620. Min Range: -5.0620
Max Act: 4.7808. Min Act: -0.1700
Data Index: 2804728 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0620. Min Range: -5.0620
Max Act: 4.7808. Min Act: -0.1700
Data Index: 5285821 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0620. Min Range: -5.0620
Max Act: 4.7495. Min Act: -0.1700
Data Index: 1814028 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0620. Min Range: -5.0620
Max Act: 4.7495. Min Act: -0.1700
Data Index: 5281741 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0620. Min Range: -5.0620
Max Act: 4.7808. Min Act: -0.1700
Data Index: 2416351 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0620. Min Range: -5.0620
Max Act: 4.7495. Min Act: -0.1700
Data Index: 1406313 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0620. Min Range: -5.0620
Max Act: 4.6870. Min Act: -0.1700
Data Index: 6562459 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0620. Min Range: -5.0620
Max Act: 4.7183. Min Act: -0.1700
Data Index: 4647237 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0620. Min Range: -5.0620
Max Act: 4.6870. Min Act: -0.1700
Data Index: 2563716 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0620. Min Range: -5.0620
Max Act: 4.6870. Min Act: -0.1700
Data Index: 7103955 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0620. Min Range: -5.0620
Max Act: 4.6245. Min Act: -0.1700
Data Index: 3162600 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0620. Min Range: -5.0620
Max Act: 4.6558. Min Act: -0.1700
Data Index: 4894419 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0620. Min Range: -5.0620
Max Act: 4.6245. Min Act: -0.1700
Data Index: 5122887 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #19