Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5228 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1121. Min Range: -6.1121
Max Act: 6.1121. Min Act: -0.1700
Data Index: 112862 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1121. Min Range: -6.1121
Max Act: 5.9871. Min Act: -0.1700
Data Index: 852476 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1121. Min Range: -6.1121
Max Act: 5.9558. Min Act: -0.1700
Data Index: 5474162 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1121. Min Range: -6.1121
Max Act: 5.9246. Min Act: -0.1700
Data Index: 4033170 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1121. Min Range: -6.1121
Max Act: 5.9246. Min Act: -0.1700
Data Index: 3012250 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1121. Min Range: -6.1121
Max Act: 5.8933. Min Act: -0.1700
Data Index: 4901443 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1121. Min Range: -6.1121
Max Act: 5.8621. Min Act: -0.1700
Data Index: 5720543 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1121. Min Range: -6.1121
Max Act: 5.8933. Min Act: -0.1700
Data Index: 3151038 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1121. Min Range: -6.1121
Max Act: 5.8621. Min Act: -0.1700
Data Index: 6353204 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1121. Min Range: -6.1121
Max Act: 5.8933. Min Act: -0.1700
Data Index: 5061244 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1121. Min Range: -6.1121
Max Act: 5.8621. Min Act: -0.1700
Data Index: 240725 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1121. Min Range: -6.1121
Max Act: 5.8621. Min Act: -0.1700
Data Index: 1396165 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1121. Min Range: -6.1121
Max Act: 5.8308. Min Act: -0.1700
Data Index: 5845666 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1121. Min Range: -6.1121
Max Act: 5.8308. Min Act: -0.1700
Data Index: 1101904 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1121. Min Range: -6.1121
Max Act: 5.8308. Min Act: -0.1700
Data Index: 4606637 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1121. Min Range: -6.1121
Max Act: 5.8308. Min Act: -0.1700
Data Index: 796149 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1121. Min Range: -6.1121
Max Act: 5.8308. Min Act: -0.1700
Data Index: 2217812 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1121. Min Range: -6.1121
Max Act: 5.7996. Min Act: -0.1700
Data Index: 5843024 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1121. Min Range: -6.1121
Max Act: 5.7996. Min Act: -0.1700
Data Index: 571456 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1121. Min Range: -6.1121
Max Act: 5.7996. Min Act: -0.1700
Data Index: 3633996 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #19