Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2885 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3471. Min Range: -8.3471
Max Act: 8.3471. Min Act: -0.1700
Data Index: 8443865 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3471. Min Range: -8.3471
Max Act: 8.2846. Min Act: -0.1700
Data Index: 4013167 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3471. Min Range: -8.3471
Max Act: 8.2846. Min Act: -0.1700
Data Index: 893909 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3471. Min Range: -8.3471
Max Act: 8.2846. Min Act: -0.1700
Data Index: 4189164 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3471. Min Range: -8.3471
Max Act: 7.9721. Min Act: -0.1700
Data Index: 2414555 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3471. Min Range: -8.3471
Max Act: 8.0033. Min Act: -0.1700
Data Index: 6959266 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3471. Min Range: -8.3471
Max Act: 7.9721. Min Act: -0.1700
Data Index: 282804 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3471. Min Range: -8.3471
Max Act: 7.9721. Min Act: -0.1700
Data Index: 8322252 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3471. Min Range: -8.3471
Max Act: 7.9096. Min Act: -0.1700
Data Index: 6201667 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3471. Min Range: -8.3471
Max Act: 7.8783. Min Act: -0.1700
Data Index: 6392097 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3471. Min Range: -8.3471
Max Act: 7.8471. Min Act: -0.1700
Data Index: 1363682 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3471. Min Range: -8.3471
Max Act: 7.8158. Min Act: -0.1700
Data Index: 8656803 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3471. Min Range: -8.3471
Max Act: 7.6908. Min Act: -0.1700
Data Index: 2722789 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3471. Min Range: -8.3471
Max Act: 7.6596. Min Act: -0.1700
Data Index: 5464456 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3471. Min Range: -8.3471
Max Act: 7.6908. Min Act: -0.1700
Data Index: 7350896 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3471. Min Range: -8.3471
Max Act: 7.6596. Min Act: -0.1700
Data Index: 3979733 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3471. Min Range: -8.3471
Max Act: 7.6596. Min Act: -0.1700
Data Index: 2873235 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3471. Min Range: -8.3471
Max Act: 7.5971. Min Act: -0.1700
Data Index: 6767170 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3471. Min Range: -8.3471
Max Act: 7.5971. Min Act: -0.1700
Data Index: 8790007 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3471. Min Range: -8.3471
Max Act: 7.5971. Min Act: -0.1700
Data Index: 5704064 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #19