Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5869 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.2899. Min Range: -9.2899
Max Act: 9.2899. Min Act: -0.1700
Data Index: 4091939 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2899. Min Range: -9.2899
Max Act: 9.1649. Min Act: -0.1700
Data Index: 4507813 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2899. Min Range: -9.2899
Max Act: 9.1649. Min Act: -0.1700
Data Index: 4302614 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2899. Min Range: -9.2899
Max Act: 9.1024. Min Act: -0.1700
Data Index: 3740930 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2899. Min Range: -9.2899
Max Act: 9.1024. Min Act: -0.1700
Data Index: 1404960 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2899. Min Range: -9.2899
Max Act: 9.0399. Min Act: -0.1700
Data Index: 843434 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2899. Min Range: -9.2899
Max Act: 9.0399. Min Act: -0.1700
Data Index: 8154793 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2899. Min Range: -9.2899
Max Act: 9.0399. Min Act: -0.1700
Data Index: 5347679 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2899. Min Range: -9.2899
Max Act: 8.9774. Min Act: -0.1700
Data Index: 6700658 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2899. Min Range: -9.2899
Max Act: 8.9774. Min Act: -0.1699
Data Index: 7099372 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2899. Min Range: -9.2899
Max Act: 8.9774. Min Act: -0.1700
Data Index: 7359215 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2899. Min Range: -9.2899
Max Act: 8.9774. Min Act: -0.1700
Data Index: 5103816 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2899. Min Range: -9.2899
Max Act: 8.9774. Min Act: -0.1700
Data Index: 2321530 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2899. Min Range: -9.2899
Max Act: 8.9774. Min Act: -0.1700
Data Index: 4459432 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2899. Min Range: -9.2899
Max Act: 8.9774. Min Act: -0.1700
Data Index: 654421 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2899. Min Range: -9.2899
Max Act: 9.0399. Min Act: -0.1700
Data Index: 6385266 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2899. Min Range: -9.2899
Max Act: 8.9774. Min Act: -0.1700
Data Index: 3120986 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2899. Min Range: -9.2899
Max Act: 8.9774. Min Act: -0.1700
Data Index: 1324223 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2899. Min Range: -9.2899
Max Act: 8.9774. Min Act: -0.1700
Data Index: 1895230 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2899. Min Range: -9.2899
Max Act: 8.9774. Min Act: -0.1700
Data Index: 8499119 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #19