Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5536 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1326. Min Range: -8.1326
Max Act: 8.1326. Min Act: -0.1700
Data Index: 5803308 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1326. Min Range: -8.1326
Max Act: 8.0701. Min Act: -0.1700
Data Index: 5711823 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1326. Min Range: -8.1326
Max Act: 8.0701. Min Act: -0.1700
Data Index: 6648873 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1326. Min Range: -8.1326
Max Act: 7.9451. Min Act: -0.1700
Data Index: 2878018 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1326. Min Range: -8.1326
Max Act: 7.8201. Min Act: -0.1700
Data Index: 2146070 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1326. Min Range: -8.1326
Max Act: 7.8201. Min Act: -0.1700
Data Index: 6532014 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1326. Min Range: -8.1326
Max Act: 7.8201. Min Act: -0.1700
Data Index: 8618800 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1326. Min Range: -8.1326
Max Act: 7.8201. Min Act: -0.1700
Data Index: 2961911 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1326. Min Range: -8.1326
Max Act: 7.7576. Min Act: -0.1700
Data Index: 7487324 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1326. Min Range: -8.1326
Max Act: 7.7576. Min Act: -0.1700
Data Index: 5377332 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1326. Min Range: -8.1326
Max Act: 7.7576. Min Act: -0.1700
Data Index: 2157821 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1326. Min Range: -8.1326
Max Act: 7.6951. Min Act: -0.1700
Data Index: 4805400 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1326. Min Range: -8.1326
Max Act: 7.6951. Min Act: -0.1700
Data Index: 787146 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1326. Min Range: -8.1326
Max Act: 7.6326. Min Act: -0.1700
Data Index: 5014094 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1326. Min Range: -8.1326
Max Act: 7.6326. Min Act: -0.1700
Data Index: 654679 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1326. Min Range: -8.1326
Max Act: 7.6326. Min Act: -0.1700
Data Index: 8216204 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1326. Min Range: -8.1326
Max Act: 7.6326. Min Act: -0.1700
Data Index: 2729453 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1326. Min Range: -8.1326
Max Act: 7.6326. Min Act: -0.1700
Data Index: 1964774 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1326. Min Range: -8.1326
Max Act: 7.6326. Min Act: -0.1700
Data Index: 6596002 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1326. Min Range: -8.1326
Max Act: 7.6951. Min Act: -0.1700
Data Index: 4082742 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #19