Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 695 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.9958. Min Range: -5.9958
Max Act: 5.9958. Min Act: -0.1700
Data Index: 4841732 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9958. Min Range: -5.9958
Max Act: 5.9333. Min Act: -0.1700
Data Index: 2846048 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9958. Min Range: -5.9958
Max Act: 5.8708. Min Act: -0.1700
Data Index: 5480732 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9958. Min Range: -5.9958
Max Act: 5.8708. Min Act: -0.1700
Data Index: 197835 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9958. Min Range: -5.9958
Max Act: 5.8083. Min Act: -0.1700
Data Index: 7930090 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9958. Min Range: -5.9958
Max Act: 5.7770. Min Act: -0.1700
Data Index: 7274091 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9958. Min Range: -5.9958
Max Act: 5.7145. Min Act: -0.1700
Data Index: 1246907 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9958. Min Range: -5.9958
Max Act: 5.7458. Min Act: -0.1700
Data Index: 5812922 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9958. Min Range: -5.9958
Max Act: 5.6833. Min Act: -0.1700
Data Index: 7400372 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9958. Min Range: -5.9958
Max Act: 5.6833. Min Act: -0.1700
Data Index: 7917862 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9958. Min Range: -5.9958
Max Act: 5.6833. Min Act: -0.1700
Data Index: 4252204 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9958. Min Range: -5.9958
Max Act: 5.6520. Min Act: -0.1700
Data Index: 6212751 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9958. Min Range: -5.9958
Max Act: 5.6833. Min Act: -0.1700
Data Index: 5962851 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9958. Min Range: -5.9958
Max Act: 5.7145. Min Act: -0.1700
Data Index: 8755517 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9958. Min Range: -5.9958
Max Act: 5.6208. Min Act: -0.1700
Data Index: 4832538 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9958. Min Range: -5.9958
Max Act: 5.6208. Min Act: -0.1700
Data Index: 671 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9958. Min Range: -5.9958
Max Act: 5.6833. Min Act: -0.1700
Data Index: 6333052 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9958. Min Range: -5.9958
Max Act: 5.6520. Min Act: -0.1700
Data Index: 2736384 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9958. Min Range: -5.9958
Max Act: 5.5895. Min Act: -0.1700
Data Index: 7128293 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9958. Min Range: -5.9958
Max Act: 5.5895. Min Act: -0.1700
Data Index: 1710836 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #19