Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4861 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7402. Min Range: -6.7402
Max Act: 6.7089. Min Act: -0.1700
Data Index: 7258902 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7402. Min Range: -6.7402
Max Act: 6.7402. Min Act: -0.1700
Data Index: 6966134 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7402. Min Range: -6.7402
Max Act: 6.6777. Min Act: -0.1700
Data Index: 6473334 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7402. Min Range: -6.7402
Max Act: 6.6777. Min Act: -0.1700
Data Index: 2505246 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7402. Min Range: -6.7402
Max Act: 6.6777. Min Act: -0.1700
Data Index: 4762825 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7402. Min Range: -6.7402
Max Act: 6.6777. Min Act: -0.1700
Data Index: 1200305 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7402. Min Range: -6.7402
Max Act: 6.6464. Min Act: -0.1700
Data Index: 7361002 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7402. Min Range: -6.7402
Max Act: 6.6464. Min Act: -0.1700
Data Index: 2088617 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7402. Min Range: -6.7402
Max Act: 6.6464. Min Act: -0.1700
Data Index: 1856635 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7402. Min Range: -6.7402
Max Act: 6.6152. Min Act: -0.1700
Data Index: 215790 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7402. Min Range: -6.7402
Max Act: 6.6152. Min Act: -0.1700
Data Index: 7761153 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7402. Min Range: -6.7402
Max Act: 6.6152. Min Act: -0.1700
Data Index: 7165516 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7402. Min Range: -6.7402
Max Act: 6.6152. Min Act: -0.1700
Data Index: 8260314 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7402. Min Range: -6.7402
Max Act: 6.5839. Min Act: -0.1700
Data Index: 4494490 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7402. Min Range: -6.7402
Max Act: 6.5839. Min Act: -0.1700
Data Index: 2749868 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7402. Min Range: -6.7402
Max Act: 6.5839. Min Act: -0.1700
Data Index: 2189669 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7402. Min Range: -6.7402
Max Act: 6.5839. Min Act: -0.1700
Data Index: 8379245 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7402. Min Range: -6.7402
Max Act: 6.5839. Min Act: -0.1700
Data Index: 613549 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7402. Min Range: -6.7402
Max Act: 6.5527. Min Act: -0.1700
Data Index: 8052846 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7402. Min Range: -6.7402
Max Act: 6.5527. Min Act: -0.1700
Data Index: 3845396 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #19