Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2565 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5097. Min Range: -6.5097
Max Act: 6.5097. Min Act: -0.1700
Data Index: 8014491 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5097. Min Range: -6.5097
Max Act: 6.2909. Min Act: -0.1700
Data Index: 281492 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5097. Min Range: -6.5097
Max Act: 6.2597. Min Act: -0.1700
Data Index: 2002045 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5097. Min Range: -6.5097
Max Act: 6.1659. Min Act: -0.1700
Data Index: 7654873 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5097. Min Range: -6.5097
Max Act: 6.0722. Min Act: -0.1700
Data Index: 7122244 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5097. Min Range: -6.5097
Max Act: 6.0409. Min Act: -0.1700
Data Index: 8124822 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5097. Min Range: -6.5097
Max Act: 6.0097. Min Act: -0.1700
Data Index: 2978122 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5097. Min Range: -6.5097
Max Act: 6.0097. Min Act: -0.1700
Data Index: 1909025 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5097. Min Range: -6.5097
Max Act: 6.0097. Min Act: -0.1700
Data Index: 8312389 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5097. Min Range: -6.5097
Max Act: 5.9784. Min Act: -0.1700
Data Index: 690636 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5097. Min Range: -6.5097
Max Act: 5.9784. Min Act: -0.1700
Data Index: 237422 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5097. Min Range: -6.5097
Max Act: 5.9472. Min Act: -0.1700
Data Index: 5052468 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5097. Min Range: -6.5097
Max Act: 5.9472. Min Act: -0.1700
Data Index: 5418738 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5097. Min Range: -6.5097
Max Act: 5.9472. Min Act: -0.1700
Data Index: 4984124 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5097. Min Range: -6.5097
Max Act: 5.9472. Min Act: -0.1700
Data Index: 1598943 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5097. Min Range: -6.5097
Max Act: 5.9159. Min Act: -0.1700
Data Index: 3536370 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5097. Min Range: -6.5097
Max Act: 5.8534. Min Act: -0.1700
Data Index: 8671370 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5097. Min Range: -6.5097
Max Act: 5.9159. Min Act: -0.1700
Data Index: 2139646 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5097. Min Range: -6.5097
Max Act: 5.8534. Min Act: -0.1700
Data Index: 6080066 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5097. Min Range: -6.5097
Max Act: 5.8222. Min Act: -0.1700
Data Index: 5482638 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #19