Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3197 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9440. Min Range: -7.9440
Max Act: 7.9440. Min Act: -0.1700
Data Index: 6448019 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9440. Min Range: -7.9440
Max Act: 7.7252. Min Act: -0.1700
Data Index: 7000934 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9440. Min Range: -7.9440
Max Act: 7.6002. Min Act: -0.1700
Data Index: 6876280 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9440. Min Range: -7.9440
Max Act: 7.4440. Min Act: -0.1700
Data Index: 6332169 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9440. Min Range: -7.9440
Max Act: 7.4127. Min Act: -0.1700
Data Index: 1359276 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9440. Min Range: -7.9440
Max Act: 7.3815. Min Act: -0.1700
Data Index: 6385105 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9440. Min Range: -7.9440
Max Act: 7.3502. Min Act: -0.1700
Data Index: 1484563 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9440. Min Range: -7.9440
Max Act: 7.1002. Min Act: -0.1700
Data Index: 5471075 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9440. Min Range: -7.9440
Max Act: 7.0690. Min Act: -0.1700
Data Index: 7192775 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9440. Min Range: -7.9440
Max Act: 6.9440. Min Act: -0.1700
Data Index: 702299 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9440. Min Range: -7.9440
Max Act: 6.9752. Min Act: -0.1700
Data Index: 3322159 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9440. Min Range: -7.9440
Max Act: 6.9440. Min Act: -0.1700
Data Index: 6537817 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9440. Min Range: -7.9440
Max Act: 6.9440. Min Act: -0.1700
Data Index: 6442803 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9440. Min Range: -7.9440
Max Act: 6.9127. Min Act: -0.1700
Data Index: 2956723 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9440. Min Range: -7.9440
Max Act: 6.8815. Min Act: -0.1700
Data Index: 1906742 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9440. Min Range: -7.9440
Max Act: 6.9127. Min Act: -0.1700
Data Index: 2683395 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9440. Min Range: -7.9440
Max Act: 6.9127. Min Act: -0.1700
Data Index: 4285518 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9440. Min Range: -7.9440
Max Act: 6.9127. Min Act: -0.1700
Data Index: 7685964 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9440. Min Range: -7.9440
Max Act: 6.8815. Min Act: -0.1700
Data Index: 558330 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9440. Min Range: -7.9440
Max Act: 6.8502. Min Act: -0.1700
Data Index: 2316950 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #19