Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2478 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1810. Min Range: -6.1810
Max Act: 6.1810. Min Act: -0.1700
Data Index: 466992 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1810. Min Range: -6.1810
Max Act: 6.1497. Min Act: -0.1700
Data Index: 6503115 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1810. Min Range: -6.1810
Max Act: 6.1497. Min Act: -0.1700
Data Index: 5919744 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1810. Min Range: -6.1810
Max Act: 6.1497. Min Act: -0.1700
Data Index: 1463476 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1810. Min Range: -6.1810
Max Act: 5.9622. Min Act: -0.1700
Data Index: 4946397 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1810. Min Range: -6.1810
Max Act: 5.8685. Min Act: -0.1700
Data Index: 414982 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1810. Min Range: -6.1810
Max Act: 5.8685. Min Act: -0.1700
Data Index: 7389575 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1810. Min Range: -6.1810
Max Act: 5.8060. Min Act: -0.1700
Data Index: 3960921 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1810. Min Range: -6.1810
Max Act: 5.8060. Min Act: -0.1700
Data Index: 6055189 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1810. Min Range: -6.1810
Max Act: 5.7747. Min Act: -0.1700
Data Index: 92566 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1810. Min Range: -6.1810
Max Act: 5.7747. Min Act: -0.1700
Data Index: 5203326 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1810. Min Range: -6.1810
Max Act: 5.7435. Min Act: -0.1700
Data Index: 3218234 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1810. Min Range: -6.1810
Max Act: 5.7435. Min Act: -0.1700
Data Index: 5919736 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1810. Min Range: -6.1810
Max Act: 5.7122. Min Act: -0.1700
Data Index: 3960923 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1810. Min Range: -6.1810
Max Act: 5.6810. Min Act: -0.1700
Data Index: 7245327 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1810. Min Range: -6.1810
Max Act: 5.6810. Min Act: -0.1700
Data Index: 5078932 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1810. Min Range: -6.1810
Max Act: 5.6810. Min Act: -0.1700
Data Index: 5078931 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1810. Min Range: -6.1810
Max Act: 5.6810. Min Act: -0.1700
Data Index: 5078933 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1810. Min Range: -6.1810
Max Act: 5.6810. Min Act: -0.1700
Data Index: 2735695 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1810. Min Range: -6.1810
Max Act: 5.6497. Min Act: -0.1700
Data Index: 8062575 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #19