Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3474 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8918. Min Range: -7.8918
Max Act: 7.8918. Min Act: -0.1700
Data Index: 5540843 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8918. Min Range: -7.8918
Max Act: 7.5480. Min Act: -0.1700
Data Index: 3528369 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8918. Min Range: -7.8918
Max Act: 7.4855. Min Act: -0.1700
Data Index: 3193634 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8918. Min Range: -7.8918
Max Act: 7.4855. Min Act: -0.1700
Data Index: 3834161 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8918. Min Range: -7.8918
Max Act: 7.3918. Min Act: -0.1700
Data Index: 7997278 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8918. Min Range: -7.8918
Max Act: 7.3918. Min Act: -0.1700
Data Index: 6239189 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8918. Min Range: -7.8918
Max Act: 7.3918. Min Act: -0.1700
Data Index: 754510 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8918. Min Range: -7.8918
Max Act: 7.2668. Min Act: -0.1700
Data Index: 5468820 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8918. Min Range: -7.8918
Max Act: 7.2668. Min Act: -0.1700
Data Index: 23620 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8918. Min Range: -7.8918
Max Act: 7.2668. Min Act: -0.1700
Data Index: 790598 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8918. Min Range: -7.8918
Max Act: 7.1730. Min Act: -0.1700
Data Index: 45305 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8918. Min Range: -7.8918
Max Act: 7.2043. Min Act: -0.1700
Data Index: 3062890 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8918. Min Range: -7.8918
Max Act: 7.1730. Min Act: -0.1700
Data Index: 3566490 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8918. Min Range: -7.8918
Max Act: 7.1730. Min Act: -0.1700
Data Index: 6509789 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8918. Min Range: -7.8918
Max Act: 7.0793. Min Act: -0.1700
Data Index: 4653685 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8918. Min Range: -7.8918
Max Act: 7.0793. Min Act: -0.1700
Data Index: 3301304 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8918. Min Range: -7.8918
Max Act: 7.0793. Min Act: -0.1700
Data Index: 3797660 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8918. Min Range: -7.8918
Max Act: 7.0480. Min Act: -0.1700
Data Index: 6323884 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8918. Min Range: -7.8918
Max Act: 7.0168. Min Act: -0.1700
Data Index: 1155795 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8918. Min Range: -7.8918
Max Act: 7.0168. Min Act: -0.1700
Data Index: 3224714 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #19