Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3874 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4725. Min Range: -4.4725
Max Act: 4.4725. Min Act: -0.1700
Data Index: 2780578 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4725. Min Range: -4.4725
Max Act: 4.4413. Min Act: -0.1700
Data Index: 1134728 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4725. Min Range: -4.4725
Max Act: 4.4413. Min Act: -0.1700
Data Index: 6212216 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4725. Min Range: -4.4725
Max Act: 4.4413. Min Act: -0.1700
Data Index: 5514086 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4725. Min Range: -4.4725
Max Act: 4.4100. Min Act: -0.1700
Data Index: 590901 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4725. Min Range: -4.4725
Max Act: 4.4100. Min Act: -0.1700
Data Index: 6815835 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4725. Min Range: -4.4725
Max Act: 4.2850. Min Act: -0.1700
Data Index: 2756564 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4725. Min Range: -4.4725
Max Act: 4.2538. Min Act: -0.1700
Data Index: 2471234 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4725. Min Range: -4.4725
Max Act: 4.2225. Min Act: -0.1700
Data Index: 672744 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4725. Min Range: -4.4725
Max Act: 4.1600. Min Act: -0.1700
Data Index: 1304943 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4725. Min Range: -4.4725
Max Act: 4.1913. Min Act: -0.1700
Data Index: 6134177 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4725. Min Range: -4.4725
Max Act: 4.1913. Min Act: -0.1700
Data Index: 97748 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4725. Min Range: -4.4725
Max Act: 4.1600. Min Act: -0.1700
Data Index: 5731198 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4725. Min Range: -4.4725
Max Act: 4.1288. Min Act: -0.1700
Data Index: 1176696 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4725. Min Range: -4.4725
Max Act: 4.1288. Min Act: -0.1700
Data Index: 4781962 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4725. Min Range: -4.4725
Max Act: 4.1288. Min Act: -0.1700
Data Index: 1727153 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4725. Min Range: -4.4725
Max Act: 4.1288. Min Act: -0.1700
Data Index: 2619746 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4725. Min Range: -4.4725
Max Act: 4.1288. Min Act: -0.1700
Data Index: 4681727 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4725. Min Range: -4.4725
Max Act: 4.0975. Min Act: -0.1700
Data Index: 3087772 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4725. Min Range: -4.4725
Max Act: 4.1288. Min Act: -0.1700
Data Index: 3937838 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #19