Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2045 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1882. Min Range: -6.1882
Max Act: 6.1882. Min Act: -0.1700
Data Index: 1860901 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1882. Min Range: -6.1882
Max Act: 6.1569. Min Act: -0.1700
Data Index: 3587310 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1882. Min Range: -6.1882
Max Act: 6.0944. Min Act: -0.1700
Data Index: 3538988 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1882. Min Range: -6.1882
Max Act: 6.1257. Min Act: -0.1700
Data Index: 1860907 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1882. Min Range: -6.1882
Max Act: 6.1569. Min Act: -0.1700
Data Index: 8348579 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1882. Min Range: -6.1882
Max Act: 6.1257. Min Act: -0.1700
Data Index: 1860903 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1882. Min Range: -6.1882
Max Act: 6.1257. Min Act: -0.1700
Data Index: 1860896 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1882. Min Range: -6.1882
Max Act: 6.0944. Min Act: -0.1700
Data Index: 6495649 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1882. Min Range: -6.1882
Max Act: 6.0944. Min Act: -0.1700
Data Index: 2634367 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1882. Min Range: -6.1882
Max Act: 6.0319. Min Act: -0.1700
Data Index: 2634365 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1882. Min Range: -6.1882
Max Act: 6.0319. Min Act: -0.1700
Data Index: 5818911 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1882. Min Range: -6.1882
Max Act: 6.0007. Min Act: -0.1700
Data Index: 2014084 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1882. Min Range: -6.1882
Max Act: 6.0007. Min Act: -0.1700
Data Index: 2634366 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1882. Min Range: -6.1882
Max Act: 6.0319. Min Act: -0.1700
Data Index: 1861154 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1882. Min Range: -6.1882
Max Act: 5.9694. Min Act: -0.1700
Data Index: 2584724 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1882. Min Range: -6.1882
Max Act: 5.9694. Min Act: -0.1700
Data Index: 1860897 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1882. Min Range: -6.1882
Max Act: 5.9694. Min Act: -0.1700
Data Index: 2440532 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1882. Min Range: -6.1882
Max Act: 5.9694. Min Act: -0.1700
Data Index: 2584725 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1882. Min Range: -6.1882
Max Act: 5.9694. Min Act: -0.1700
Data Index: 781989 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1882. Min Range: -6.1882
Max Act: 5.9694. Min Act: -0.1700
Data Index: 1644558 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #19