Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3431 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4829. Min Range: -3.4829
Max Act: 3.4829. Min Act: -0.1700
Data Index: 5220885 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4829. Min Range: -3.4829
Max Act: 3.4673. Min Act: -0.1700
Data Index: 6496716 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4829. Min Range: -3.4829
Max Act: 3.4673. Min Act: -0.1700
Data Index: 1819295 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4829. Min Range: -3.4829
Max Act: 3.4203. Min Act: -0.1700
Data Index: 5314694 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4829. Min Range: -3.4829
Max Act: 3.4359. Min Act: -0.1700
Data Index: 6997478 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4829. Min Range: -3.4829
Max Act: 3.4203. Min Act: -0.1700
Data Index: 6463835 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4829. Min Range: -3.4829
Max Act: 3.4046. Min Act: -0.1700
Data Index: 7554157 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4829. Min Range: -3.4829
Max Act: 3.3889. Min Act: -0.1700
Data Index: 6449632 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4829. Min Range: -3.4829
Max Act: 3.3732. Min Act: -0.1700
Data Index: 6240154 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4829. Min Range: -3.4829
Max Act: 3.3732. Min Act: -0.1700
Data Index: 2135627 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4829. Min Range: -3.4829
Max Act: 3.3575. Min Act: -0.1700
Data Index: 6240162 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4829. Min Range: -3.4829
Max Act: 3.3575. Min Act: -0.1700
Data Index: 7975240 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4829. Min Range: -3.4829
Max Act: 3.3575. Min Act: -0.1700
Data Index: 5314697 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4829. Min Range: -3.4829
Max Act: 3.3419. Min Act: -0.1700
Data Index: 2264946 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4829. Min Range: -3.4829
Max Act: 3.3732. Min Act: -0.1700
Data Index: 1819294 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4829. Min Range: -3.4829
Max Act: 3.3262. Min Act: -0.1700
Data Index: 7375981 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4829. Min Range: -3.4829
Max Act: 3.3262. Min Act: -0.1700
Data Index: 6018325 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4829. Min Range: -3.4829
Max Act: 3.3262. Min Act: -0.1700
Data Index: 7718644 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4829. Min Range: -3.4829
Max Act: 3.3105. Min Act: -0.1700
Data Index: 2489149 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4829. Min Range: -3.4829
Max Act: 3.3262. Min Act: -0.1700
Data Index: 7165409 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #19