Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5782 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5058. Min Range: -4.5058
Max Act: 4.5058. Min Act: -0.1700
Data Index: 1853303 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5058. Min Range: -4.5058
Max Act: 4.4746. Min Act: -0.1700
Data Index: 105876 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5058. Min Range: -4.5058
Max Act: 4.2558. Min Act: -0.1700
Data Index: 1351996 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5058. Min Range: -4.5058
Max Act: 4.2558. Min Act: -0.1700
Data Index: 7428325 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5058. Min Range: -4.5058
Max Act: 4.2245. Min Act: -0.1700
Data Index: 4178552 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5058. Min Range: -4.5058
Max Act: 4.1620. Min Act: -0.1700
Data Index: 2636171 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5058. Min Range: -4.5058
Max Act: 4.1620. Min Act: -0.1700
Data Index: 7922213 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5058. Min Range: -4.5058
Max Act: 4.1308. Min Act: -0.1700
Data Index: 2891749 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5058. Min Range: -4.5058
Max Act: 4.0995. Min Act: -0.1700
Data Index: 5951451 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5058. Min Range: -4.5058
Max Act: 4.0995. Min Act: -0.1700
Data Index: 4815164 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5058. Min Range: -4.5058
Max Act: 4.0995. Min Act: -0.1700
Data Index: 4586301 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5058. Min Range: -4.5058
Max Act: 4.0995. Min Act: -0.1700
Data Index: 725446 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5058. Min Range: -4.5058
Max Act: 4.0995. Min Act: -0.1700
Data Index: 4107838 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5058. Min Range: -4.5058
Max Act: 4.0995. Min Act: -0.1700
Data Index: 643012 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5058. Min Range: -4.5058
Max Act: 4.0995. Min Act: -0.1700
Data Index: 2671727 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5058. Min Range: -4.5058
Max Act: 4.0995. Min Act: -0.1700
Data Index: 3240646 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5058. Min Range: -4.5058
Max Act: 4.0995. Min Act: -0.1700
Data Index: 3646323 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5058. Min Range: -4.5058
Max Act: 4.0683. Min Act: -0.1700
Data Index: 2940988 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5058. Min Range: -4.5058
Max Act: 4.0683. Min Act: -0.1700
Data Index: 7244900 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5058. Min Range: -4.5058
Max Act: 4.0995. Min Act: -0.1700
Data Index: 6786020 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #19