Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2015 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.2633. Min Range: -6.2633
Max Act: 6.2633. Min Act: -0.1700
Data Index: 7934113 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2633. Min Range: -6.2633
Max Act: 6.2320. Min Act: -0.1700
Data Index: 2517727 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2633. Min Range: -6.2633
Max Act: 6.2008. Min Act: -0.1700
Data Index: 383646 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2633. Min Range: -6.2633
Max Act: 6.1695. Min Act: -0.1700
Data Index: 3813439 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2633. Min Range: -6.2633
Max Act: 6.1695. Min Act: -0.1700
Data Index: 2656822 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2633. Min Range: -6.2633
Max Act: 6.1383. Min Act: -0.1700
Data Index: 5932777 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2633. Min Range: -6.2633
Max Act: 6.1695. Min Act: -0.1700
Data Index: 8144788 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2633. Min Range: -6.2633
Max Act: 6.0758. Min Act: -0.1700
Data Index: 725098 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2633. Min Range: -6.2633
Max Act: 6.1383. Min Act: -0.1700
Data Index: 8435734 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2633. Min Range: -6.2633
Max Act: 6.0758. Min Act: -0.1700
Data Index: 4610880 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2633. Min Range: -6.2633
Max Act: 6.1070. Min Act: -0.1700
Data Index: 2984140 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2633. Min Range: -6.2633
Max Act: 6.0758. Min Act: -0.1700
Data Index: 8758113 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2633. Min Range: -6.2633
Max Act: 6.1070. Min Act: -0.1700
Data Index: 340920 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2633. Min Range: -6.2633
Max Act: 6.0758. Min Act: -0.1700
Data Index: 5558193 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2633. Min Range: -6.2633
Max Act: 6.0445. Min Act: -0.1700
Data Index: 8651158 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2633. Min Range: -6.2633
Max Act: 6.0133. Min Act: -0.1700
Data Index: 6536243 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2633. Min Range: -6.2633
Max Act: 5.9820. Min Act: -0.1700
Data Index: 6696321 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2633. Min Range: -6.2633
Max Act: 6.0445. Min Act: -0.1700
Data Index: 2150098 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2633. Min Range: -6.2633
Max Act: 5.9508. Min Act: -0.1700
Data Index: 4659465 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2633. Min Range: -6.2633
Max Act: 5.9508. Min Act: -0.1700
Data Index: 5926006 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #19