Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2821 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8914. Min Range: -6.8914
Max Act: 6.8914. Min Act: -0.1700
Data Index: 6504320 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8914. Min Range: -6.8914
Max Act: 6.7664. Min Act: -0.1700
Data Index: 1583934 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8914. Min Range: -6.8914
Max Act: 6.6726. Min Act: -0.1700
Data Index: 1914820 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8914. Min Range: -6.8914
Max Act: 6.6414. Min Act: -0.1700
Data Index: 1085207 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8914. Min Range: -6.8914
Max Act: 6.6414. Min Act: -0.1700
Data Index: 6763430 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8914. Min Range: -6.8914
Max Act: 6.6101. Min Act: -0.1700
Data Index: 1624466 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8914. Min Range: -6.8914
Max Act: 6.6414. Min Act: -0.1700
Data Index: 4268887 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8914. Min Range: -6.8914
Max Act: 6.5789. Min Act: -0.1700
Data Index: 7946104 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8914. Min Range: -6.8914
Max Act: 6.5476. Min Act: -0.1700
Data Index: 3701122 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8914. Min Range: -6.8914
Max Act: 6.5476. Min Act: -0.1700
Data Index: 7500559 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8914. Min Range: -6.8914
Max Act: 6.5476. Min Act: -0.1700
Data Index: 378718 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8914. Min Range: -6.8914
Max Act: 6.5476. Min Act: -0.1700
Data Index: 958774 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8914. Min Range: -6.8914
Max Act: 6.5476. Min Act: -0.1700
Data Index: 7959138 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8914. Min Range: -6.8914
Max Act: 6.5164. Min Act: -0.1700
Data Index: 1583938 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8914. Min Range: -6.8914
Max Act: 6.5164. Min Act: -0.1700
Data Index: 1207307 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8914. Min Range: -6.8914
Max Act: 6.5164. Min Act: -0.1700
Data Index: 7429021 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8914. Min Range: -6.8914
Max Act: 6.5164. Min Act: -0.1700
Data Index: 7009818 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8914. Min Range: -6.8914
Max Act: 6.5164. Min Act: -0.1700
Data Index: 3156567 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8914. Min Range: -6.8914
Max Act: 6.5164. Min Act: -0.1700
Data Index: 5797350 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8914. Min Range: -6.8914
Max Act: 6.5164. Min Act: -0.1700
Data Index: 5482658 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #19