Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3559 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.5851. Min Range: -2.5851
Max Act: 2.5851. Min Act: -0.1700
Data Index: 7250333 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5851. Min Range: -2.5851
Max Act: 2.5528. Min Act: -0.1700
Data Index: 531708 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5851. Min Range: -2.5851
Max Act: 2.5528. Min Act: -0.1700
Data Index: 8717460 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5851. Min Range: -2.5851
Max Act: 2.5528. Min Act: -0.1700
Data Index: 2793649 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5851. Min Range: -2.5851
Max Act: 2.5043. Min Act: -0.1700
Data Index: 3406129 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5851. Min Range: -2.5851
Max Act: 2.4881. Min Act: -0.1700
Data Index: 7983231 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5851. Min Range: -2.5851
Max Act: 2.4881. Min Act: -0.1700
Data Index: 6456165 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5851. Min Range: -2.5851
Max Act: 2.4881. Min Act: -0.1700
Data Index: 5435007 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5851. Min Range: -2.5851
Max Act: 2.4881. Min Act: -0.1700
Data Index: 4651131 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5851. Min Range: -2.5851
Max Act: 2.4719. Min Act: -0.1700
Data Index: 2836760 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5851. Min Range: -2.5851
Max Act: 2.4719. Min Act: -0.1700
Data Index: 7277889 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5851. Min Range: -2.5851
Max Act: 2.4557. Min Act: -0.1700
Data Index: 5506644 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5851. Min Range: -2.5851
Max Act: 2.4557. Min Act: -0.1700
Data Index: 1210796 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5851. Min Range: -2.5851
Max Act: 2.4394. Min Act: -0.1700
Data Index: 3102585 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5851. Min Range: -2.5851
Max Act: 2.4557. Min Act: -0.1700
Data Index: 6198420 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5851. Min Range: -2.5851
Max Act: 2.4394. Min Act: -0.1700
Data Index: 587671 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5851. Min Range: -2.5851
Max Act: 2.4394. Min Act: -0.1700
Data Index: 4120778 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5851. Min Range: -2.5851
Max Act: 2.4394. Min Act: -0.1700
Data Index: 3598080 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5851. Min Range: -2.5851
Max Act: 2.4231. Min Act: -0.1700
Data Index: 2129500 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5851. Min Range: -2.5851
Max Act: 2.4231. Min Act: -0.1700
Data Index: 2170691 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19