Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3218 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.5739. Min Range: -3.5739
Max Act: 3.5739. Min Act: -0.1700
Data Index: 6838215 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5739. Min Range: -3.5739
Max Act: 3.4330. Min Act: -0.1700
Data Index: 5563462 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5739. Min Range: -3.5739
Max Act: 3.3859. Min Act: -0.1700
Data Index: 8830742 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5739. Min Range: -3.5739
Max Act: 3.3075. Min Act: -0.1700
Data Index: 8832492 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5739. Min Range: -3.5739
Max Act: 3.2918. Min Act: -0.1700
Data Index: 1807268 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5739. Min Range: -3.5739
Max Act: 3.2918. Min Act: -0.1700
Data Index: 6115779 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5739. Min Range: -3.5739
Max Act: 3.2761. Min Act: -0.1700
Data Index: 2410280 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5739. Min Range: -3.5739
Max Act: 3.2761. Min Act: -0.1700
Data Index: 2357558 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5739. Min Range: -3.5739
Max Act: 3.2761. Min Act: -0.1700
Data Index: 8615834 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5739. Min Range: -3.5739
Max Act: 3.2761. Min Act: -0.1700
Data Index: 1956585 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5739. Min Range: -3.5739
Max Act: 3.2604. Min Act: -0.1700
Data Index: 5941077 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5739. Min Range: -3.5739
Max Act: 3.2447. Min Act: -0.1700
Data Index: 5905962 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5739. Min Range: -3.5739
Max Act: 3.2290. Min Act: -0.1700
Data Index: 6428185 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5739. Min Range: -3.5739
Max Act: 3.2290. Min Act: -0.1700
Data Index: 1556993 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5739. Min Range: -3.5739
Max Act: 3.2290. Min Act: -0.1700
Data Index: 5964028 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5739. Min Range: -3.5739
Max Act: 3.2290. Min Act: -0.1700
Data Index: 124949 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5739. Min Range: -3.5739
Max Act: 3.2290. Min Act: -0.1700
Data Index: 3512313 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5739. Min Range: -3.5739
Max Act: 3.2447. Min Act: -0.1700
Data Index: 4373294 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5739. Min Range: -3.5739
Max Act: 3.2290. Min Act: -0.1700
Data Index: 1826374 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5739. Min Range: -3.5739
Max Act: 3.2290. Min Act: -0.1700
Data Index: 4889488 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #19