Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1126 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0955. Min Range: -8.0955
Max Act: 8.0955. Min Act: -0.1700
Data Index: 3624907 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0955. Min Range: -8.0955
Max Act: 8.0955. Min Act: -0.1700
Data Index: 5418527 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0955. Min Range: -8.0955
Max Act: 8.0955. Min Act: -0.1700
Data Index: 8531890 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0955. Min Range: -8.0955
Max Act: 7.9705. Min Act: -0.1700
Data Index: 2455896 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0955. Min Range: -8.0955
Max Act: 7.9705. Min Act: -0.1700
Data Index: 8589358 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0955. Min Range: -8.0955
Max Act: 7.9705. Min Act: -0.1700
Data Index: 8634531 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0955. Min Range: -8.0955
Max Act: 7.8455. Min Act: -0.1700
Data Index: 4734342 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0955. Min Range: -8.0955
Max Act: 7.8455. Min Act: -0.1700
Data Index: 1469822 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0955. Min Range: -8.0955
Max Act: 7.8455. Min Act: -0.1700
Data Index: 4149092 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0955. Min Range: -8.0955
Max Act: 7.7830. Min Act: -0.1700
Data Index: 1204473 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0955. Min Range: -8.0955
Max Act: 7.7830. Min Act: -0.1700
Data Index: 5618591 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0955. Min Range: -8.0955
Max Act: 7.7830. Min Act: -0.1700
Data Index: 2641121 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0955. Min Range: -8.0955
Max Act: 7.7830. Min Act: -0.1700
Data Index: 8574645 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0955. Min Range: -8.0955
Max Act: 7.7830. Min Act: -0.1700
Data Index: 6580433 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0955. Min Range: -8.0955
Max Act: 7.7205. Min Act: -0.1700
Data Index: 3305443 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0955. Min Range: -8.0955
Max Act: 7.7205. Min Act: -0.1700
Data Index: 6725799 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0955. Min Range: -8.0955
Max Act: 7.7205. Min Act: -0.1700
Data Index: 812912 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0955. Min Range: -8.0955
Max Act: 7.6580. Min Act: -0.1700
Data Index: 4636483 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0955. Min Range: -8.0955
Max Act: 7.6580. Min Act: -0.1700
Data Index: 2041308 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0955. Min Range: -8.0955
Max Act: 7.6580. Min Act: -0.1700
Data Index: 6364238 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #19