Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3724 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8456. Min Range: -5.8456
Max Act: 5.8456. Min Act: -0.1700
Data Index: 834252 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8456. Min Range: -5.8456
Max Act: 5.5956. Min Act: -0.1700
Data Index: 2146060 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8456. Min Range: -5.8456
Max Act: 5.5644. Min Act: -0.1700
Data Index: 4588132 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8456. Min Range: -5.8456
Max Act: 5.5644. Min Act: -0.1700
Data Index: 3860970 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8456. Min Range: -5.8456
Max Act: 5.5019. Min Act: -0.1700
Data Index: 1324981 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8456. Min Range: -5.8456
Max Act: 5.4394. Min Act: -0.1700
Data Index: 533152 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8456. Min Range: -5.8456
Max Act: 5.4081. Min Act: -0.1700
Data Index: 4970321 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8456. Min Range: -5.8456
Max Act: 5.4081. Min Act: -0.1700
Data Index: 2504654 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8456. Min Range: -5.8456
Max Act: 5.3769. Min Act: -0.1700
Data Index: 3360287 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8456. Min Range: -5.8456
Max Act: 5.3769. Min Act: -0.1700
Data Index: 7931918 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8456. Min Range: -5.8456
Max Act: 5.3456. Min Act: -0.1700
Data Index: 3159000 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8456. Min Range: -5.8456
Max Act: 5.3456. Min Act: -0.1700
Data Index: 2135826 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8456. Min Range: -5.8456
Max Act: 5.3456. Min Act: -0.1700
Data Index: 4878923 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8456. Min Range: -5.8456
Max Act: 5.3144. Min Act: -0.1700
Data Index: 3167845 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8456. Min Range: -5.8456
Max Act: 5.3144. Min Act: -0.1700
Data Index: 4960430 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8456. Min Range: -5.8456
Max Act: 5.2831. Min Act: -0.1700
Data Index: 6908025 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8456. Min Range: -5.8456
Max Act: 5.2831. Min Act: -0.1700
Data Index: 1268150 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8456. Min Range: -5.8456
Max Act: 5.2519. Min Act: -0.1700
Data Index: 1138187 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8456. Min Range: -5.8456
Max Act: 5.2206. Min Act: -0.1700
Data Index: 3238526 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8456. Min Range: -5.8456
Max Act: 5.2519. Min Act: -0.1700
Data Index: 565756 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #19