Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2882 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0926. Min Range: -7.0926
Max Act: 7.0926. Min Act: -0.1700
Data Index: 1546757 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0926. Min Range: -7.0926
Max Act: 6.9988. Min Act: -0.1700
Data Index: 1954898 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0926. Min Range: -7.0926
Max Act: 6.9051. Min Act: -0.1700
Data Index: 1308297 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0926. Min Range: -7.0926
Max Act: 6.8738. Min Act: -0.1700
Data Index: 5526572 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0926. Min Range: -7.0926
Max Act: 6.8738. Min Act: -0.1700
Data Index: 6496124 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0926. Min Range: -7.0926
Max Act: 6.8113. Min Act: -0.1700
Data Index: 2952234 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0926. Min Range: -7.0926
Max Act: 6.8426. Min Act: -0.1700
Data Index: 514307 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0926. Min Range: -7.0926
Max Act: 6.8113. Min Act: -0.1700
Data Index: 6964371 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0926. Min Range: -7.0926
Max Act: 6.7801. Min Act: -0.1700
Data Index: 1176452 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0926. Min Range: -7.0926
Max Act: 6.7801. Min Act: -0.1700
Data Index: 8549419 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0926. Min Range: -7.0926
Max Act: 6.7801. Min Act: -0.1700
Data Index: 8114278 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0926. Min Range: -7.0926
Max Act: 6.7488. Min Act: -0.1700
Data Index: 6729616 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0926. Min Range: -7.0926
Max Act: 6.7176. Min Act: -0.1700
Data Index: 977380 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0926. Min Range: -7.0926
Max Act: 6.6863. Min Act: -0.1700
Data Index: 1284822 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0926. Min Range: -7.0926
Max Act: 6.6551. Min Act: -0.1700
Data Index: 3717032 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0926. Min Range: -7.0926
Max Act: 6.6238. Min Act: -0.1700
Data Index: 6056143 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0926. Min Range: -7.0926
Max Act: 6.6238. Min Act: -0.1700
Data Index: 4993177 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0926. Min Range: -7.0926
Max Act: 6.6238. Min Act: -0.1700
Data Index: 5084175 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0926. Min Range: -7.0926
Max Act: 6.6238. Min Act: -0.1700
Data Index: 8463153 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0926. Min Range: -7.0926
Max Act: 6.6238. Min Act: -0.1700
Data Index: 5460227 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #19