Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2109 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 10.0866. Min Range: -10.0866
Max Act: 10.0866. Min Act: -0.1700
Data Index: 6236961 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.0866. Min Range: -10.0866
Max Act: 9.8991. Min Act: -0.1700
Data Index: 8532642 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.0866. Min Range: -10.0866
Max Act: 9.8991. Min Act: -0.1700
Data Index: 1933269 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.0866. Min Range: -10.0866
Max Act: 9.8991. Min Act: -0.1700
Data Index: 3491440 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.0866. Min Range: -10.0866
Max Act: 9.9616. Min Act: -0.1700
Data Index: 7481875 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.0866. Min Range: -10.0866
Max Act: 9.8366. Min Act: -0.1700
Data Index: 3468458 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.0866. Min Range: -10.0866
Max Act: 9.8366. Min Act: -0.1700
Data Index: 1130586 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.0866. Min Range: -10.0866
Max Act: 9.7741. Min Act: -0.1700
Data Index: 3768788 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.0866. Min Range: -10.0866
Max Act: 9.7741. Min Act: -0.1700
Data Index: 7613782 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.0866. Min Range: -10.0866
Max Act: 9.7741. Min Act: -0.1700
Data Index: 7148729 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.0866. Min Range: -10.0866
Max Act: 9.7741. Min Act: -0.1700
Data Index: 3483377 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.0866. Min Range: -10.0866
Max Act: 9.7116. Min Act: -0.1700
Data Index: 6197665 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.0866. Min Range: -10.0866
Max Act: 9.7116. Min Act: -0.1700
Data Index: 7143026 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.0866. Min Range: -10.0866
Max Act: 9.7116. Min Act: -0.1700
Data Index: 7345154 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.0866. Min Range: -10.0866
Max Act: 9.6491. Min Act: -0.1700
Data Index: 8499361 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.0866. Min Range: -10.0866
Max Act: 9.7116. Min Act: -0.1700
Data Index: 3024352 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.0866. Min Range: -10.0866
Max Act: 9.7116. Min Act: -0.1700
Data Index: 4274339 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.0866. Min Range: -10.0866
Max Act: 9.7116. Min Act: -0.1700
Data Index: 1492369 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.0866. Min Range: -10.0866
Max Act: 9.6491. Min Act: -0.1700
Data Index: 2287635 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.0866. Min Range: -10.0866
Max Act: 9.6491. Min Act: -0.1700
Data Index: 7128293 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #19