Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4917 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1679. Min Range: -4.1679
Max Act: 4.1679. Min Act: -0.1700
Data Index: 8619006 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1679. Min Range: -4.1679
Max Act: 4.1679. Min Act: -0.1700
Data Index: 5739412 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1679. Min Range: -4.1679
Max Act: 4.1054. Min Act: -0.1700
Data Index: 5483345 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1679. Min Range: -4.1679
Max Act: 4.1054. Min Act: -0.1700
Data Index: 5023329 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1679. Min Range: -4.1679
Max Act: 4.1054. Min Act: -0.1700
Data Index: 6507951 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1679. Min Range: -4.1679
Max Act: 4.0116. Min Act: -0.1700
Data Index: 4023372 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1679. Min Range: -4.1679
Max Act: 4.0429. Min Act: -0.1700
Data Index: 4316090 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1679. Min Range: -4.1679
Max Act: 4.0429. Min Act: -0.1700
Data Index: 3134122 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1679. Min Range: -4.1679
Max Act: 4.0116. Min Act: -0.1700
Data Index: 712481 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1679. Min Range: -4.1679
Max Act: 3.9804. Min Act: -0.1700
Data Index: 412172 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1679. Min Range: -4.1679
Max Act: 3.9804. Min Act: -0.1700
Data Index: 6328300 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1679. Min Range: -4.1679
Max Act: 3.9804. Min Act: -0.1700
Data Index: 1889259 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1679. Min Range: -4.1679
Max Act: 3.9491. Min Act: -0.1700
Data Index: 4455167 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1679. Min Range: -4.1679
Max Act: 3.9491. Min Act: -0.1700
Data Index: 2220705 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1679. Min Range: -4.1679
Max Act: 3.9491. Min Act: -0.1700
Data Index: 8332258 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1679. Min Range: -4.1679
Max Act: 3.9491. Min Act: -0.1700
Data Index: 6934079 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1679. Min Range: -4.1679
Max Act: 3.9178. Min Act: -0.1700
Data Index: 2267713 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1679. Min Range: -4.1679
Max Act: 3.9178. Min Act: -0.1700
Data Index: 6836086 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1679. Min Range: -4.1679
Max Act: 3.8866. Min Act: -0.1700
Data Index: 6784136 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1679. Min Range: -4.1679
Max Act: 3.8866. Min Act: -0.1700
Data Index: 5262506 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #19