Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3618 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8653. Min Range: -8.8653
Max Act: 8.8028. Min Act: -0.1700
Data Index: 3303384 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8653. Min Range: -8.8653
Max Act: 8.8653. Min Act: -0.1700
Data Index: 6939329 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8653. Min Range: -8.8653
Max Act: 8.6778. Min Act: -0.1700
Data Index: 5917141 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8653. Min Range: -8.8653
Max Act: 8.6153. Min Act: -0.1700
Data Index: 7343382 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8653. Min Range: -8.8653
Max Act: 8.5528. Min Act: -0.1700
Data Index: 5980390 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8653. Min Range: -8.8653
Max Act: 8.5528. Min Act: -0.1700
Data Index: 7278406 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8653. Min Range: -8.8653
Max Act: 8.5528. Min Act: -0.1700
Data Index: 616392 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8653. Min Range: -8.8653
Max Act: 8.5528. Min Act: -0.1700
Data Index: 408043 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8653. Min Range: -8.8653
Max Act: 8.4903. Min Act: -0.1700
Data Index: 3040754 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8653. Min Range: -8.8653
Max Act: 8.5528. Min Act: -0.1700
Data Index: 771413 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8653. Min Range: -8.8653
Max Act: 8.4903. Min Act: -0.1700
Data Index: 1701668 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8653. Min Range: -8.8653
Max Act: 8.4903. Min Act: -0.1700
Data Index: 3049637 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8653. Min Range: -8.8653
Max Act: 8.4903. Min Act: -0.1700
Data Index: 5271107 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8653. Min Range: -8.8653
Max Act: 8.4903. Min Act: -0.1700
Data Index: 804197 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8653. Min Range: -8.8653
Max Act: 8.4903. Min Act: -0.1700
Data Index: 2948106 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8653. Min Range: -8.8653
Max Act: 8.4278. Min Act: -0.1700
Data Index: 149223 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8653. Min Range: -8.8653
Max Act: 8.4278. Min Act: -0.1700
Data Index: 1582225 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8653. Min Range: -8.8653
Max Act: 8.4278. Min Act: -0.1700
Data Index: 1931793 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8653. Min Range: -8.8653
Max Act: 8.4903. Min Act: -0.1700
Data Index: 708079 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8653. Min Range: -8.8653
Max Act: 8.4278. Min Act: -0.1700
Data Index: 6285049 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #19