Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 727 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4910. Min Range: -6.4910
Max Act: 6.4910. Min Act: -0.1700
Data Index: 7295883 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4910. Min Range: -6.4910
Max Act: 6.4598. Min Act: -0.1700
Data Index: 5031907 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4910. Min Range: -6.4910
Max Act: 6.2723. Min Act: -0.1700
Data Index: 3716491 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4910. Min Range: -6.4910
Max Act: 6.2098. Min Act: -0.1700
Data Index: 59489 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4910. Min Range: -6.4910
Max Act: 6.0848. Min Act: -0.1700
Data Index: 2902563 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4910. Min Range: -6.4910
Max Act: 6.0223. Min Act: -0.1700
Data Index: 2151020 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4910. Min Range: -6.4910
Max Act: 5.9910. Min Act: -0.1700
Data Index: 2700808 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4910. Min Range: -6.4910
Max Act: 5.9910. Min Act: -0.1700
Data Index: 5562024 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4910. Min Range: -6.4910
Max Act: 5.9910. Min Act: -0.1700
Data Index: 4855142 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4910. Min Range: -6.4910
Max Act: 5.9910. Min Act: -0.1700
Data Index: 8362443 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4910. Min Range: -6.4910
Max Act: 5.9910. Min Act: -0.1700
Data Index: 3373119 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4910. Min Range: -6.4910
Max Act: 5.9598. Min Act: -0.1700
Data Index: 5106820 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4910. Min Range: -6.4910
Max Act: 5.9285. Min Act: -0.1700
Data Index: 3658398 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4910. Min Range: -6.4910
Max Act: 5.9285. Min Act: -0.1700
Data Index: 301943 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4910. Min Range: -6.4910
Max Act: 5.9285. Min Act: -0.1700
Data Index: 2747218 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4910. Min Range: -6.4910
Max Act: 5.9598. Min Act: -0.1700
Data Index: 5299738 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4910. Min Range: -6.4910
Max Act: 5.8973. Min Act: -0.1700
Data Index: 1375131 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4910. Min Range: -6.4910
Max Act: 5.8973. Min Act: -0.1700
Data Index: 8141933 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4910. Min Range: -6.4910
Max Act: 5.8973. Min Act: -0.1700
Data Index: 4560923 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4910. Min Range: -6.4910
Max Act: 5.8973. Min Act: -0.1700
Data Index: 1453390 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #19