Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3888 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5747. Min Range: -3.5747
Max Act: 3.5747. Min Act: -0.1700
Data Index: 5603638 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5747. Min Range: -3.5747
Max Act: 3.5747. Min Act: -0.1700
Data Index: 4441986 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5747. Min Range: -3.5747
Max Act: 3.5434. Min Act: -0.1700
Data Index: 3205788 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5747. Min Range: -3.5747
Max Act: 3.5434. Min Act: -0.1700
Data Index: 1414846 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5747. Min Range: -3.5747
Max Act: 3.5434. Min Act: -0.1700
Data Index: 5082897 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5747. Min Range: -3.5747
Max Act: 3.5121. Min Act: -0.1700
Data Index: 1332204 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5747. Min Range: -3.5747
Max Act: 3.5434. Min Act: -0.1700
Data Index: 2837688 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5747. Min Range: -3.5747
Max Act: 3.5434. Min Act: -0.1700
Data Index: 4548066 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5747. Min Range: -3.5747
Max Act: 3.5434. Min Act: -0.1700
Data Index: 2437054 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5747. Min Range: -3.5747
Max Act: 3.5121. Min Act: -0.1700
Data Index: 3012902 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5747. Min Range: -3.5747
Max Act: 3.5121. Min Act: -0.1700
Data Index: 465663 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5747. Min Range: -3.5747
Max Act: 3.5121. Min Act: -0.1700
Data Index: 4535350 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5747. Min Range: -3.5747
Max Act: 3.5121. Min Act: -0.1700
Data Index: 2729066 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5747. Min Range: -3.5747
Max Act: 3.5121. Min Act: -0.1700
Data Index: 4501178 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5747. Min Range: -3.5747
Max Act: 3.5121. Min Act: -0.1700
Data Index: 4297504 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5747. Min Range: -3.5747
Max Act: 3.5121. Min Act: -0.1700
Data Index: 344891 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5747. Min Range: -3.5747
Max Act: 3.4808. Min Act: -0.1700
Data Index: 344828 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5747. Min Range: -3.5747
Max Act: 3.5121. Min Act: -0.1700
Data Index: 4169753 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5747. Min Range: -3.5747
Max Act: 3.5121. Min Act: -0.1700
Data Index: 2040008 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5747. Min Range: -3.5747
Max Act: 3.5121. Min Act: -0.1700
Data Index: 1995152 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #19