Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1787 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7386. Min Range: -3.7386
Max Act: 3.7386. Min Act: -0.1700
Data Index: 6027655 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7386. Min Range: -3.7386
Max Act: 3.6447. Min Act: -0.1700
Data Index: 5354370 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7386. Min Range: -3.7386
Max Act: 3.6134. Min Act: -0.1700
Data Index: 8668790 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7386. Min Range: -3.7386
Max Act: 3.5821. Min Act: -0.1700
Data Index: 2763054 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7386. Min Range: -3.7386
Max Act: 3.5821. Min Act: -0.1700
Data Index: 3849752 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7386. Min Range: -3.7386
Max Act: 3.5508. Min Act: -0.1700
Data Index: 5074194 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7386. Min Range: -3.7386
Max Act: 3.5195. Min Act: -0.1700
Data Index: 7632799 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7386. Min Range: -3.7386
Max Act: 3.5195. Min Act: -0.1700
Data Index: 7439547 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7386. Min Range: -3.7386
Max Act: 3.5195. Min Act: -0.1700
Data Index: 2493629 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7386. Min Range: -3.7386
Max Act: 3.5508. Min Act: -0.1700
Data Index: 5348891 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7386. Min Range: -3.7386
Max Act: 3.4882. Min Act: -0.1700
Data Index: 4517749 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7386. Min Range: -3.7386
Max Act: 3.4882. Min Act: -0.1700
Data Index: 314709 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7386. Min Range: -3.7386
Max Act: 3.4882. Min Act: -0.1700
Data Index: 27013 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7386. Min Range: -3.7386
Max Act: 3.4882. Min Act: -0.1700
Data Index: 6451880 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7386. Min Range: -3.7386
Max Act: 3.4882. Min Act: -0.1700
Data Index: 1796855 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7386. Min Range: -3.7386
Max Act: 3.4882. Min Act: -0.1700
Data Index: 4317252 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7386. Min Range: -3.7386
Max Act: 3.4882. Min Act: -0.1700
Data Index: 5421530 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7386. Min Range: -3.7386
Max Act: 3.4882. Min Act: -0.1700
Data Index: 7192265 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7386. Min Range: -3.7386
Max Act: 3.4882. Min Act: -0.1700
Data Index: 1645541 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7386. Min Range: -3.7386
Max Act: 3.4882. Min Act: -0.1700
Data Index: 7468500 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #19