Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5393 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8344. Min Range: -6.8344
Max Act: 6.8344. Min Act: -0.1700
Data Index: 6452843 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8344. Min Range: -6.8344
Max Act: 6.8344. Min Act: -0.1700
Data Index: 6524797 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8344. Min Range: -6.8344
Max Act: 6.6469. Min Act: -0.1700
Data Index: 6412662 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8344. Min Range: -6.8344
Max Act: 6.5844. Min Act: -0.1700
Data Index: 6251219 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8344. Min Range: -6.8344
Max Act: 6.5844. Min Act: -0.1700
Data Index: 979278 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8344. Min Range: -6.8344
Max Act: 6.5531. Min Act: -0.1700
Data Index: 4617619 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8344. Min Range: -6.8344
Max Act: 6.4594. Min Act: -0.1700
Data Index: 5233443 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8344. Min Range: -6.8344
Max Act: 6.4594. Min Act: -0.1700
Data Index: 1719325 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8344. Min Range: -6.8344
Max Act: 6.3969. Min Act: -0.1700
Data Index: 2066042 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8344. Min Range: -6.8344
Max Act: 6.3969. Min Act: -0.1700
Data Index: 3217639 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8344. Min Range: -6.8344
Max Act: 6.3969. Min Act: -0.1700
Data Index: 582217 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8344. Min Range: -6.8344
Max Act: 6.3969. Min Act: -0.1700
Data Index: 7490268 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8344. Min Range: -6.8344
Max Act: 6.3656. Min Act: -0.1700
Data Index: 7836129 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8344. Min Range: -6.8344
Max Act: 6.3969. Min Act: -0.1700
Data Index: 1496894 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8344. Min Range: -6.8344
Max Act: 6.3656. Min Act: -0.1700
Data Index: 3307973 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8344. Min Range: -6.8344
Max Act: 6.3344. Min Act: -0.1700
Data Index: 1844447 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8344. Min Range: -6.8344
Max Act: 6.3344. Min Act: -0.1700
Data Index: 3682875 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8344. Min Range: -6.8344
Max Act: 6.3344. Min Act: -0.1700
Data Index: 7072816 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8344. Min Range: -6.8344
Max Act: 6.2719. Min Act: -0.1699
Data Index: 48860 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8344. Min Range: -6.8344
Max Act: 6.2719. Min Act: -0.1700
Data Index: 2733830 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #19