Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3999 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8591. Min Range: -7.8591
Max Act: 7.8591. Min Act: -0.1700
Data Index: 39043 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8591. Min Range: -7.8591
Max Act: 7.8591. Min Act: -0.1700
Data Index: 491186 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8591. Min Range: -7.8591
Max Act: 7.7341. Min Act: -0.1700
Data Index: 4844791 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8591. Min Range: -7.8591
Max Act: 7.7028. Min Act: -0.1700
Data Index: 3745905 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8591. Min Range: -7.8591
Max Act: 7.7028. Min Act: -0.1700
Data Index: 8231994 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8591. Min Range: -7.8591
Max Act: 7.7028. Min Act: -0.1700
Data Index: 4525676 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8591. Min Range: -7.8591
Max Act: 7.6403. Min Act: -0.1700
Data Index: 2563746 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8591. Min Range: -7.8591
Max Act: 7.5778. Min Act: -0.1700
Data Index: 6270439 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8591. Min Range: -7.8591
Max Act: 7.5778. Min Act: -0.1700
Data Index: 8298590 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8591. Min Range: -7.8591
Max Act: 7.5466. Min Act: -0.1700
Data Index: 3445305 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8591. Min Range: -7.8591
Max Act: 7.5466. Min Act: -0.1700
Data Index: 7128336 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8591. Min Range: -7.8591
Max Act: 7.5466. Min Act: -0.1700
Data Index: 5320360 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8591. Min Range: -7.8591
Max Act: 7.5466. Min Act: -0.1700
Data Index: 961459 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8591. Min Range: -7.8591
Max Act: 7.5153. Min Act: -0.1700
Data Index: 6588347 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8591. Min Range: -7.8591
Max Act: 7.4841. Min Act: -0.1700
Data Index: 7939792 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8591. Min Range: -7.8591
Max Act: 7.4528. Min Act: -0.1700
Data Index: 2052700 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8591. Min Range: -7.8591
Max Act: 7.4216. Min Act: -0.1700
Data Index: 206619 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8591. Min Range: -7.8591
Max Act: 7.4841. Min Act: -0.1700
Data Index: 8640950 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8591. Min Range: -7.8591
Max Act: 7.4528. Min Act: -0.1700
Data Index: 4319569 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8591. Min Range: -7.8591
Max Act: 7.4216. Min Act: -0.1700
Data Index: 4834342 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #19