Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5548 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0412. Min Range: -6.0412
Max Act: 6.0412. Min Act: -0.1700
Data Index: 6358508 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0412. Min Range: -6.0412
Max Act: 5.9162. Min Act: -0.1700
Data Index: 1582398 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0412. Min Range: -6.0412
Max Act: 5.8850. Min Act: -0.1698
Data Index: 4579057 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0412. Min Range: -6.0412
Max Act: 5.8225. Min Act: -0.1700
Data Index: 2540729 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0412. Min Range: -6.0412
Max Act: 5.7912. Min Act: -0.1700
Data Index: 3349697 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0412. Min Range: -6.0412
Max Act: 5.7912. Min Act: -0.1700
Data Index: 5647566 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0412. Min Range: -6.0412
Max Act: 5.7912. Min Act: -0.1700
Data Index: 5406658 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0412. Min Range: -6.0412
Max Act: 5.7600. Min Act: -0.1700
Data Index: 5647572 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0412. Min Range: -6.0412
Max Act: 5.7600. Min Act: -0.1700
Data Index: 4432851 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0412. Min Range: -6.0412
Max Act: 5.7600. Min Act: -0.1700
Data Index: 6744129 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0412. Min Range: -6.0412
Max Act: 5.7600. Min Act: -0.1700
Data Index: 1415406 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0412. Min Range: -6.0412
Max Act: 5.7287. Min Act: -0.1700
Data Index: 8806173 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0412. Min Range: -6.0412
Max Act: 5.7287. Min Act: -0.1700
Data Index: 8613698 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0412. Min Range: -6.0412
Max Act: 5.7287. Min Act: -0.1700
Data Index: 8291749 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0412. Min Range: -6.0412
Max Act: 5.7287. Min Act: -0.1700
Data Index: 2570935 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0412. Min Range: -6.0412
Max Act: 5.7287. Min Act: -0.1700
Data Index: 7686934 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0412. Min Range: -6.0412
Max Act: 5.7287. Min Act: -0.1700
Data Index: 297906 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0412. Min Range: -6.0412
Max Act: 5.6975. Min Act: -0.1700
Data Index: 835443 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0412. Min Range: -6.0412
Max Act: 5.7287. Min Act: -0.1700
Data Index: 6177267 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0412. Min Range: -6.0412
Max Act: 5.7287. Min Act: -0.1697
Data Index: 1032579 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #19