Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 591 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.5025. Min Range: -9.5025
Max Act: 9.5025. Min Act: -0.1700
Data Index: 575625 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5025. Min Range: -9.5025
Max Act: 9.1275. Min Act: -0.1700
Data Index: 7161951 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5025. Min Range: -9.5025
Max Act: 9.0650. Min Act: -0.1700
Data Index: 7173376 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5025. Min Range: -9.5025
Max Act: 9.0025. Min Act: -0.1700
Data Index: 4868821 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5025. Min Range: -9.5025
Max Act: 9.0025. Min Act: -0.1700
Data Index: 2768525 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5025. Min Range: -9.5025
Max Act: 8.9400. Min Act: -0.1700
Data Index: 2488988 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5025. Min Range: -9.5025
Max Act: 8.8775. Min Act: -0.1700
Data Index: 5775824 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5025. Min Range: -9.5025
Max Act: 8.8150. Min Act: -0.1700
Data Index: 3914009 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5025. Min Range: -9.5025
Max Act: 8.8150. Min Act: -0.1700
Data Index: 3897626 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5025. Min Range: -9.5025
Max Act: 8.8150. Min Act: -0.1700
Data Index: 6231324 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5025. Min Range: -9.5025
Max Act: 8.8150. Min Act: -0.1700
Data Index: 4255587 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5025. Min Range: -9.5025
Max Act: 8.7525. Min Act: -0.1700
Data Index: 726945 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5025. Min Range: -9.5025
Max Act: 8.7525. Min Act: -0.1700
Data Index: 3981498 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5025. Min Range: -9.5025
Max Act: 8.7525. Min Act: -0.1700
Data Index: 3362423 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5025. Min Range: -9.5025
Max Act: 8.6900. Min Act: -0.1700
Data Index: 1354847 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5025. Min Range: -9.5025
Max Act: 8.7525. Min Act: -0.1700
Data Index: 120697 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5025. Min Range: -9.5025
Max Act: 8.5650. Min Act: -0.1700
Data Index: 2376933 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5025. Min Range: -9.5025
Max Act: 8.6275. Min Act: -0.1700
Data Index: 8357804 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5025. Min Range: -9.5025
Max Act: 8.6900. Min Act: -0.1700
Data Index: 3819899 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5025. Min Range: -9.5025
Max Act: 8.5650. Min Act: -0.1700
Data Index: 6169450 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #19