Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2569 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9471. Min Range: -4.9471
Max Act: 4.9471. Min Act: -0.1700
Data Index: 799570 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9471. Min Range: -4.9471
Max Act: 4.9471. Min Act: -0.1700
Data Index: 2117216 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9471. Min Range: -4.9471
Max Act: 4.9158. Min Act: -0.1700
Data Index: 8532547 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9471. Min Range: -4.9471
Max Act: 4.8846. Min Act: -0.1700
Data Index: 4505814 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9471. Min Range: -4.9471
Max Act: 4.8846. Min Act: -0.1700
Data Index: 1728813 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9471. Min Range: -4.9471
Max Act: 4.8846. Min Act: -0.1700
Data Index: 312073 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9471. Min Range: -4.9471
Max Act: 4.8846. Min Act: -0.1700
Data Index: 6370600 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9471. Min Range: -4.9471
Max Act: 4.8221. Min Act: -0.1700
Data Index: 5068667 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9471. Min Range: -4.9471
Max Act: 4.8533. Min Act: -0.1700
Data Index: 4452658 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9471. Min Range: -4.9471
Max Act: 4.8533. Min Act: -0.1700
Data Index: 6795932 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9471. Min Range: -4.9471
Max Act: 4.8533. Min Act: -0.1700
Data Index: 4659643 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9471. Min Range: -4.9471
Max Act: 4.8221. Min Act: -0.1700
Data Index: 7725561 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9471. Min Range: -4.9471
Max Act: 4.8221. Min Act: -0.1700
Data Index: 1818716 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9471. Min Range: -4.9471
Max Act: 4.8221. Min Act: -0.1700
Data Index: 1111412 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9471. Min Range: -4.9471
Max Act: 4.8221. Min Act: -0.1700
Data Index: 2185905 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9471. Min Range: -4.9471
Max Act: 4.8221. Min Act: -0.1700
Data Index: 6795936 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9471. Min Range: -4.9471
Max Act: 4.7908. Min Act: -0.1700
Data Index: 6795937 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9471. Min Range: -4.9471
Max Act: 4.7908. Min Act: -0.1700
Data Index: 1111409 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9471. Min Range: -4.9471
Max Act: 4.7908. Min Act: -0.1700
Data Index: 563726 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9471. Min Range: -4.9471
Max Act: 4.7908. Min Act: -0.1700
Data Index: 1144277 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #19