Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3682 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0797. Min Range: -6.0797
Max Act: 6.0797. Min Act: -0.1700
Data Index: 3278817 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0797. Min Range: -6.0797
Max Act: 5.9547. Min Act: -0.1700
Data Index: 3632662 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0797. Min Range: -6.0797
Max Act: 5.8922. Min Act: -0.1700
Data Index: 5669646 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0797. Min Range: -6.0797
Max Act: 5.8922. Min Act: -0.1700
Data Index: 5364616 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0797. Min Range: -6.0797
Max Act: 5.8297. Min Act: -0.1700
Data Index: 1895939 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0797. Min Range: -6.0797
Max Act: 5.8297. Min Act: -0.1700
Data Index: 500775 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0797. Min Range: -6.0797
Max Act: 5.7672. Min Act: -0.1700
Data Index: 3810963 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0797. Min Range: -6.0797
Max Act: 5.7047. Min Act: -0.1700
Data Index: 189260 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0797. Min Range: -6.0797
Max Act: 5.7047. Min Act: -0.1700
Data Index: 7246301 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0797. Min Range: -6.0797
Max Act: 5.7047. Min Act: -0.1700
Data Index: 6967919 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0797. Min Range: -6.0797
Max Act: 5.6735. Min Act: -0.1700
Data Index: 3329421 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0797. Min Range: -6.0797
Max Act: 5.6735. Min Act: -0.1700
Data Index: 8181952 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0797. Min Range: -6.0797
Max Act: 5.6422. Min Act: -0.1700
Data Index: 7603747 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0797. Min Range: -6.0797
Max Act: 5.6422. Min Act: -0.1700
Data Index: 4818985 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0797. Min Range: -6.0797
Max Act: 5.6422. Min Act: -0.1700
Data Index: 1813043 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0797. Min Range: -6.0797
Max Act: 5.6110. Min Act: -0.1700
Data Index: 500774 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0797. Min Range: -6.0797
Max Act: 5.6422. Min Act: -0.1700
Data Index: 3609909 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0797. Min Range: -6.0797
Max Act: 5.5797. Min Act: -0.1700
Data Index: 4165010 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0797. Min Range: -6.0797
Max Act: 5.5797. Min Act: -0.1700
Data Index: 199235 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0797. Min Range: -6.0797
Max Act: 5.5172. Min Act: -0.1700
Data Index: 2234163 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #19