Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6330 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5937. Min Range: -8.5937
Max Act: 8.5937. Min Act: -0.1700
Data Index: 4825243 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5937. Min Range: -8.5937
Max Act: 8.4687. Min Act: -0.1700
Data Index: 82591 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5937. Min Range: -8.5937
Max Act: 8.2187. Min Act: -0.1700
Data Index: 3616233 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5937. Min Range: -8.5937
Max Act: 8.2187. Min Act: -0.1700
Data Index: 4336339 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5937. Min Range: -8.5937
Max Act: 7.9062. Min Act: -0.1700
Data Index: 3127028 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5937. Min Range: -8.5937
Max Act: 7.9062. Min Act: -0.1700
Data Index: 1914864 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5937. Min Range: -8.5937
Max Act: 7.9062. Min Act: -0.1700
Data Index: 1501372 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5937. Min Range: -8.5937
Max Act: 7.9062. Min Act: -0.1700
Data Index: 5792564 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5937. Min Range: -8.5937
Max Act: 7.8437. Min Act: -0.1700
Data Index: 3296461 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5937. Min Range: -8.5937
Max Act: 7.8437. Min Act: -0.1700
Data Index: 8228837 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5937. Min Range: -8.5937
Max Act: 7.8437. Min Act: -0.1700
Data Index: 1979566 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5937. Min Range: -8.5937
Max Act: 7.7812. Min Act: -0.1700
Data Index: 5231011 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5937. Min Range: -8.5937
Max Act: 7.7812. Min Act: -0.1700
Data Index: 1588642 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5937. Min Range: -8.5937
Max Act: 7.7812. Min Act: -0.1700
Data Index: 7549852 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5937. Min Range: -8.5937
Max Act: 7.7812. Min Act: -0.1700
Data Index: 5689060 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5937. Min Range: -8.5937
Max Act: 7.7812. Min Act: -0.1700
Data Index: 5872002 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5937. Min Range: -8.5937
Max Act: 7.7812. Min Act: -0.1700
Data Index: 2810166 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5937. Min Range: -8.5937
Max Act: 7.6874. Min Act: -0.1700
Data Index: 6646794 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5937. Min Range: -8.5937
Max Act: 7.7187. Min Act: -0.1700
Data Index: 3319086 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5937. Min Range: -8.5937
Max Act: 7.7187. Min Act: -0.1700
Data Index: 1072634 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #19