Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2955 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3057. Min Range: -3.3057
Max Act: 3.3057. Min Act: -0.1700
Data Index: 3841169 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3057. Min Range: -3.3057
Max Act: 3.3057. Min Act: -0.1700
Data Index: 4641861 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3057. Min Range: -3.3057
Max Act: 3.0698. Min Act: -0.1700
Data Index: 7435139 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3057. Min Range: -3.3057
Max Act: 3.1013. Min Act: -0.1700
Data Index: 1035034 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3057. Min Range: -3.3057
Max Act: 3.0540. Min Act: -0.1700
Data Index: 5416335 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3057. Min Range: -3.3057
Max Act: 3.0540. Min Act: -0.1700
Data Index: 5254751 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3057. Min Range: -3.3057
Max Act: 3.0382. Min Act: -0.1700
Data Index: 6260709 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3057. Min Range: -3.3057
Max Act: 3.0224. Min Act: -0.1700
Data Index: 8674205 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3057. Min Range: -3.3057
Max Act: 3.0224. Min Act: -0.1700
Data Index: 7753273 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3057. Min Range: -3.3057
Max Act: 3.0066. Min Act: -0.1700
Data Index: 7661990 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3057. Min Range: -3.3057
Max Act: 2.9908. Min Act: -0.1700
Data Index: 7753274 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3057. Min Range: -3.3057
Max Act: 2.9750. Min Act: -0.1700
Data Index: 7989218 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3057. Min Range: -3.3057
Max Act: 2.9908. Min Act: -0.1700
Data Index: 4814820 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3057. Min Range: -3.3057
Max Act: 2.9750. Min Act: -0.1700
Data Index: 498822 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3057. Min Range: -3.3057
Max Act: 2.9750. Min Act: -0.1700
Data Index: 7096612 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3057. Min Range: -3.3057
Max Act: 2.9750. Min Act: -0.1700
Data Index: 2478853 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3057. Min Range: -3.3057
Max Act: 2.9592. Min Act: -0.1700
Data Index: 732993 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3057. Min Range: -3.3057
Max Act: 2.9592. Min Act: -0.1700
Data Index: 1328161 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3057. Min Range: -3.3057
Max Act: 2.9592. Min Act: -0.1700
Data Index: 4919095 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3057. Min Range: -3.3057
Max Act: 2.9592. Min Act: -0.1700
Data Index: 7907706 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #19