Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2559 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5098. Min Range: -5.5098
Max Act: 5.5098. Min Act: -0.1700
Data Index: 631253 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5098. Min Range: -5.5098
Max Act: 5.4785. Min Act: -0.1700
Data Index: 6752142 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5098. Min Range: -5.5098
Max Act: 5.3848. Min Act: -0.1700
Data Index: 5241489 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5098. Min Range: -5.5098
Max Act: 5.3535. Min Act: -0.1700
Data Index: 5238601 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5098. Min Range: -5.5098
Max Act: 5.2598. Min Act: -0.1700
Data Index: 7288524 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5098. Min Range: -5.5098
Max Act: 5.2598. Min Act: -0.1700
Data Index: 1274498 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5098. Min Range: -5.5098
Max Act: 5.2285. Min Act: -0.1700
Data Index: 6153760 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5098. Min Range: -5.5098
Max Act: 5.1973. Min Act: -0.1700
Data Index: 723487 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5098. Min Range: -5.5098
Max Act: 5.1660. Min Act: -0.1700
Data Index: 3678183 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5098. Min Range: -5.5098
Max Act: 5.1660. Min Act: -0.1700
Data Index: 6310371 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5098. Min Range: -5.5098
Max Act: 5.1035. Min Act: -0.1700
Data Index: 653875 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5098. Min Range: -5.5098
Max Act: 5.1035. Min Act: -0.1700
Data Index: 7836221 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5098. Min Range: -5.5098
Max Act: 5.1035. Min Act: -0.1700
Data Index: 2989791 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5098. Min Range: -5.5098
Max Act: 5.1035. Min Act: -0.1700
Data Index: 2401186 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5098. Min Range: -5.5098
Max Act: 5.1035. Min Act: -0.1700
Data Index: 6484165 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5098. Min Range: -5.5098
Max Act: 5.1035. Min Act: -0.1700
Data Index: 4265400 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5098. Min Range: -5.5098
Max Act: 5.1035. Min Act: -0.1700
Data Index: 8410233 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5098. Min Range: -5.5098
Max Act: 5.0723. Min Act: -0.1700
Data Index: 5045490 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5098. Min Range: -5.5098
Max Act: 5.0410. Min Act: -0.1700
Data Index: 6647995 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5098. Min Range: -5.5098
Max Act: 5.0098. Min Act: -0.1700
Data Index: 7102687 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #19