Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4870 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2926. Min Range: -4.2926
Max Act: 4.2926. Min Act: -0.1700
Data Index: 3769595 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2926. Min Range: -4.2926
Max Act: 4.2614. Min Act: -0.1700
Data Index: 7860370 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2926. Min Range: -4.2926
Max Act: 4.2301. Min Act: -0.1700
Data Index: 426572 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2926. Min Range: -4.2926
Max Act: 4.1988. Min Act: -0.1700
Data Index: 6066867 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2926. Min Range: -4.2926
Max Act: 4.1988. Min Act: -0.1700
Data Index: 720363 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2926. Min Range: -4.2926
Max Act: 4.1988. Min Act: -0.1700
Data Index: 3676340 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2926. Min Range: -4.2926
Max Act: 4.1676. Min Act: -0.1700
Data Index: 3269924 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2926. Min Range: -4.2926
Max Act: 4.1363. Min Act: -0.1700
Data Index: 6057775 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2926. Min Range: -4.2926
Max Act: 4.1051. Min Act: -0.1700
Data Index: 7774836 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2926. Min Range: -4.2926
Max Act: 4.0738. Min Act: -0.1700
Data Index: 3827471 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2926. Min Range: -4.2926
Max Act: 4.0738. Min Act: -0.1700
Data Index: 7770620 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2926. Min Range: -4.2926
Max Act: 4.0738. Min Act: -0.1700
Data Index: 4040723 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2926. Min Range: -4.2926
Max Act: 4.0426. Min Act: -0.1700
Data Index: 8624770 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2926. Min Range: -4.2926
Max Act: 4.0426. Min Act: -0.1700
Data Index: 2585827 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2926. Min Range: -4.2926
Max Act: 4.0426. Min Act: -0.1700
Data Index: 1439956 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2926. Min Range: -4.2926
Max Act: 4.0426. Min Act: -0.1700
Data Index: 836518 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2926. Min Range: -4.2926
Max Act: 4.0426. Min Act: -0.1700
Data Index: 3508857 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2926. Min Range: -4.2926
Max Act: 4.0426. Min Act: -0.1700
Data Index: 2904606 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2926. Min Range: -4.2926
Max Act: 4.0113. Min Act: -0.1700
Data Index: 2402858 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2926. Min Range: -4.2926
Max Act: 4.0113. Min Act: -0.1700
Data Index: 1113693 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #19