Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2062 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7938. Min Range: -6.7938
Max Act: 6.7938. Min Act: -0.1700
Data Index: 3774673 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7938. Min Range: -6.7938
Max Act: 6.7000. Min Act: -0.1700
Data Index: 8338170 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7938. Min Range: -6.7938
Max Act: 6.5750. Min Act: -0.1700
Data Index: 1292726 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7938. Min Range: -6.7938
Max Act: 6.6063. Min Act: -0.1700
Data Index: 3401869 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7938. Min Range: -6.7938
Max Act: 6.5125. Min Act: -0.1700
Data Index: 2671476 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7938. Min Range: -6.7938
Max Act: 6.5125. Min Act: -0.1700
Data Index: 6640179 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7938. Min Range: -6.7938
Max Act: 6.5125. Min Act: -0.1700
Data Index: 7165152 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7938. Min Range: -6.7938
Max Act: 6.5125. Min Act: -0.1700
Data Index: 1265954 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7938. Min Range: -6.7938
Max Act: 6.4813. Min Act: -0.1700
Data Index: 5347487 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7938. Min Range: -6.7938
Max Act: 6.4813. Min Act: -0.1700
Data Index: 1287744 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7938. Min Range: -6.7938
Max Act: 6.4500. Min Act: -0.1700
Data Index: 4210002 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7938. Min Range: -6.7938
Max Act: 6.4500. Min Act: -0.1700
Data Index: 3285229 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7938. Min Range: -6.7938
Max Act: 6.4500. Min Act: -0.1700
Data Index: 3565928 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7938. Min Range: -6.7938
Max Act: 6.4188. Min Act: -0.1700
Data Index: 3988594 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7938. Min Range: -6.7938
Max Act: 6.4500. Min Act: -0.1700
Data Index: 6856247 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7938. Min Range: -6.7938
Max Act: 6.4188. Min Act: -0.1700
Data Index: 3232456 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7938. Min Range: -6.7938
Max Act: 6.3875. Min Act: -0.1700
Data Index: 1090333 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7938. Min Range: -6.7938
Max Act: 6.3875. Min Act: -0.1700
Data Index: 2850646 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7938. Min Range: -6.7938
Max Act: 6.3563. Min Act: -0.1700
Data Index: 2354493 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7938. Min Range: -6.7938
Max Act: 6.3250. Min Act: -0.1700
Data Index: 8085122 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #19