Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2748 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9353. Min Range: -5.9353
Max Act: 5.9353. Min Act: -0.1700
Data Index: 614517 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9353. Min Range: -5.9353
Max Act: 5.7791. Min Act: -0.1700
Data Index: 7056427 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9353. Min Range: -5.9353
Max Act: 5.5603. Min Act: -0.1700
Data Index: 2898490 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9353. Min Range: -5.9353
Max Act: 5.5291. Min Act: -0.1700
Data Index: 4889005 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9353. Min Range: -5.9353
Max Act: 5.5291. Min Act: -0.1700
Data Index: 1141264 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9353. Min Range: -5.9353
Max Act: 5.5291. Min Act: -0.1700
Data Index: 586695 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9353. Min Range: -5.9353
Max Act: 5.4666. Min Act: -0.1700
Data Index: 4288124 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9353. Min Range: -5.9353
Max Act: 5.4353. Min Act: -0.1700
Data Index: 5975103 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9353. Min Range: -5.9353
Max Act: 5.4353. Min Act: -0.1700
Data Index: 4027323 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9353. Min Range: -5.9353
Max Act: 5.4353. Min Act: -0.1700
Data Index: 5953148 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9353. Min Range: -5.9353
Max Act: 5.4041. Min Act: -0.1700
Data Index: 2319907 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9353. Min Range: -5.9353
Max Act: 5.4041. Min Act: -0.1700
Data Index: 4317507 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9353. Min Range: -5.9353
Max Act: 5.3728. Min Act: -0.1700
Data Index: 7780972 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9353. Min Range: -5.9353
Max Act: 5.3728. Min Act: -0.1700
Data Index: 5598086 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9353. Min Range: -5.9353
Max Act: 5.3103. Min Act: -0.1700
Data Index: 5293499 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9353. Min Range: -5.9353
Max Act: 5.3416. Min Act: -0.1700
Data Index: 2003843 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9353. Min Range: -5.9353
Max Act: 5.3416. Min Act: -0.1700
Data Index: 7407138 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9353. Min Range: -5.9353
Max Act: 5.3103. Min Act: -0.1700
Data Index: 4461858 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9353. Min Range: -5.9353
Max Act: 5.3103. Min Act: -0.1700
Data Index: 3143707 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9353. Min Range: -5.9353
Max Act: 5.2478. Min Act: -0.1700
Data Index: 2003841 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #19