Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3931 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1298. Min Range: -8.1298
Max Act: 8.1298. Min Act: -0.1700
Data Index: 1677728 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1298. Min Range: -8.1298
Max Act: 8.0673. Min Act: -0.1700
Data Index: 3734111 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1298. Min Range: -8.1298
Max Act: 8.0048. Min Act: -0.1700
Data Index: 3022591 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1298. Min Range: -8.1298
Max Act: 7.9736. Min Act: -0.1700
Data Index: 8423666 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1298. Min Range: -8.1298
Max Act: 7.9423. Min Act: -0.1700
Data Index: 2285863 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1298. Min Range: -8.1298
Max Act: 7.9111. Min Act: -0.1700
Data Index: 4899883 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1298. Min Range: -8.1298
Max Act: 7.9423. Min Act: -0.1700
Data Index: 5468096 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1298. Min Range: -8.1298
Max Act: 7.9423. Min Act: -0.1700
Data Index: 10512 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1298. Min Range: -8.1298
Max Act: 7.9423. Min Act: -0.1700
Data Index: 4072262 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1298. Min Range: -8.1298
Max Act: 7.9111. Min Act: -0.1700
Data Index: 6423805 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1298. Min Range: -8.1298
Max Act: 7.8798. Min Act: -0.1700
Data Index: 3667764 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1298. Min Range: -8.1298
Max Act: 7.8486. Min Act: -0.1700
Data Index: 560605 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1298. Min Range: -8.1298
Max Act: 7.8486. Min Act: -0.1700
Data Index: 5754764 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1298. Min Range: -8.1298
Max Act: 7.8486. Min Act: -0.1700
Data Index: 4115457 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1298. Min Range: -8.1298
Max Act: 7.8486. Min Act: -0.1700
Data Index: 3523486 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1298. Min Range: -8.1298
Max Act: 7.8486. Min Act: -0.1700
Data Index: 96364 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1298. Min Range: -8.1298
Max Act: 7.8486. Min Act: -0.1700
Data Index: 7482739 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1298. Min Range: -8.1298
Max Act: 7.8486. Min Act: -0.1700
Data Index: 7998972 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1298. Min Range: -8.1298
Max Act: 7.8798. Min Act: -0.1700
Data Index: 3695145 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1298. Min Range: -8.1298
Max Act: 7.7861. Min Act: -0.1700
Data Index: 7249541 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #19