Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 530 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3867. Min Range: -4.3867
Max Act: 4.3867. Min Act: -0.1700
Data Index: 4435443 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3867. Min Range: -4.3867
Max Act: 4.1679. Min Act: -0.1700
Data Index: 5381898 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3867. Min Range: -4.3867
Max Act: 4.1366. Min Act: -0.1700
Data Index: 4636344 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3867. Min Range: -4.3867
Max Act: 4.0429. Min Act: -0.1700
Data Index: 6184163 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3867. Min Range: -4.3867
Max Act: 4.0429. Min Act: -0.1700
Data Index: 5316296 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3867. Min Range: -4.3867
Max Act: 4.0116. Min Act: -0.1700
Data Index: 4937003 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3867. Min Range: -4.3867
Max Act: 3.9804. Min Act: -0.1700
Data Index: 5912361 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3867. Min Range: -4.3867
Max Act: 3.9804. Min Act: -0.1700
Data Index: 8734142 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3867. Min Range: -4.3867
Max Act: 3.9491. Min Act: -0.1700
Data Index: 2677390 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3867. Min Range: -4.3867
Max Act: 3.9491. Min Act: -0.1700
Data Index: 1772084 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3867. Min Range: -4.3867
Max Act: 3.9178. Min Act: -0.1700
Data Index: 4853801 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3867. Min Range: -4.3867
Max Act: 3.9178. Min Act: -0.1700
Data Index: 8823473 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3867. Min Range: -4.3867
Max Act: 3.9178. Min Act: -0.1700
Data Index: 1950093 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3867. Min Range: -4.3867
Max Act: 3.8866. Min Act: -0.1700
Data Index: 3594126 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3867. Min Range: -4.3867
Max Act: 3.8866. Min Act: -0.1700
Data Index: 2638945 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3867. Min Range: -4.3867
Max Act: 3.8866. Min Act: -0.1700
Data Index: 8088110 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3867. Min Range: -4.3867
Max Act: 3.8866. Min Act: -0.1700
Data Index: 2808607 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3867. Min Range: -4.3867
Max Act: 3.8866. Min Act: -0.1700
Data Index: 5291776 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3867. Min Range: -4.3867
Max Act: 3.8553. Min Act: -0.1700
Data Index: 6907240 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3867. Min Range: -4.3867
Max Act: 3.8553. Min Act: -0.1700
Data Index: 6046544 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #19