Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1751 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 0.9470. Min Range: -0.9470
Max Act: 0.9470. Min Act: -0.1698
Data Index: 3161386 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.9470. Min Range: -0.9470
Max Act: 0.9384. Min Act: -0.1700
Data Index: 7569166 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.9470. Min Range: -0.9470
Max Act: 0.9298. Min Act: -0.1696
Data Index: 4815330 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.9470. Min Range: -0.9470
Max Act: 0.9212. Min Act: -0.1687
Data Index: 8180223 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.9470. Min Range: -0.9470
Max Act: 0.9298. Min Act: -0.1700
Data Index: 3968857 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.9470. Min Range: -0.9470
Max Act: 0.9212. Min Act: -0.1700
Data Index: 6263938 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.9470. Min Range: -0.9470
Max Act: 0.9127. Min Act: -0.1695
Data Index: 7197319 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.9470. Min Range: -0.9470
Max Act: 0.9127. Min Act: -0.1700
Data Index: 820874 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.9470. Min Range: -0.9470
Max Act: 0.8955. Min Act: -0.1700
Data Index: 850883 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.9470. Min Range: -0.9470
Max Act: 0.8955. Min Act: -0.1700
Data Index: 8395123 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.9470. Min Range: -0.9470
Max Act: 0.8785. Min Act: -0.1699
Data Index: 4793583 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.9470. Min Range: -0.9470
Max Act: 0.8870. Min Act: -0.1700
Data Index: 65930 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.9470. Min Range: -0.9470
Max Act: 0.8785. Min Act: -0.1700
Data Index: 2445055 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.9470. Min Range: -0.9470
Max Act: 0.8699. Min Act: -0.1698
Data Index: 3511865 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.9470. Min Range: -0.9470
Max Act: 0.8699. Min Act: -0.1700
Data Index: 3511867 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.9470. Min Range: -0.9470
Max Act: 0.8614. Min Act: -0.1700
Data Index: 2433031 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.9470. Min Range: -0.9470
Max Act: 0.8699. Min Act: -0.1699
Data Index: 5052077 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.9470. Min Range: -0.9470
Max Act: 0.8699. Min Act: -0.1700
Data Index: 6602796 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.9470. Min Range: -0.9470
Max Act: 0.8699. Min Act: -0.1675
Data Index: 1220049 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.9470. Min Range: -0.9470
Max Act: 0.8699. Min Act: -0.1687
Data Index: 1015425 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #19