Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4048 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4246. Min Range: -8.4246
Max Act: 8.4246. Min Act: -0.1700
Data Index: 5714428 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4246. Min Range: -8.4246
Max Act: 7.7996. Min Act: -0.1700
Data Index: 1704545 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4246. Min Range: -8.4246
Max Act: 7.7371. Min Act: -0.1700
Data Index: 895268 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4246. Min Range: -8.4246
Max Act: 7.7371. Min Act: -0.1700
Data Index: 8769290 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4246. Min Range: -8.4246
Max Act: 7.7683. Min Act: -0.1700
Data Index: 7543848 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4246. Min Range: -8.4246
Max Act: 7.7371. Min Act: -0.1700
Data Index: 6552313 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4246. Min Range: -8.4246
Max Act: 7.7371. Min Act: -0.1700
Data Index: 7242081 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4246. Min Range: -8.4246
Max Act: 7.7371. Min Act: -0.1700
Data Index: 2702942 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4246. Min Range: -8.4246
Max Act: 7.7058. Min Act: -0.1700
Data Index: 5210313 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4246. Min Range: -8.4246
Max Act: 7.7058. Min Act: -0.1700
Data Index: 3072625 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4246. Min Range: -8.4246
Max Act: 7.6746. Min Act: -0.1700
Data Index: 863389 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4246. Min Range: -8.4246
Max Act: 7.6746. Min Act: -0.1700
Data Index: 8614764 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4246. Min Range: -8.4246
Max Act: 7.6746. Min Act: -0.1700
Data Index: 233137 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4246. Min Range: -8.4246
Max Act: 7.6433. Min Act: -0.1700
Data Index: 8598444 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4246. Min Range: -8.4246
Max Act: 7.6433. Min Act: -0.1700
Data Index: 5038367 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4246. Min Range: -8.4246
Max Act: 7.6433. Min Act: -0.1700
Data Index: 5675643 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4246. Min Range: -8.4246
Max Act: 7.6433. Min Act: -0.1700
Data Index: 603802 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4246. Min Range: -8.4246
Max Act: 7.6121. Min Act: -0.1700
Data Index: 653887 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4246. Min Range: -8.4246
Max Act: 7.6121. Min Act: -0.1700
Data Index: 6780849 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4246. Min Range: -8.4246
Max Act: 7.5808. Min Act: -0.1700
Data Index: 4256383 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #19