Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1509 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1121. Min Range: -9.1121
Max Act: 9.1121. Min Act: -0.1700
Data Index: 4548385 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1121. Min Range: -9.1121
Max Act: 8.7996. Min Act: -0.1700
Data Index: 3430033 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1121. Min Range: -9.1121
Max Act: 8.7996. Min Act: -0.1700
Data Index: 7190377 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1121. Min Range: -9.1121
Max Act: 8.7996. Min Act: -0.1700
Data Index: 5953450 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1121. Min Range: -9.1121
Max Act: 8.6746. Min Act: -0.1700
Data Index: 123195 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1121. Min Range: -9.1121
Max Act: 8.6121. Min Act: -0.1700
Data Index: 8137101 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1121. Min Range: -9.1121
Max Act: 8.6746. Min Act: -0.1700
Data Index: 4827322 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1121. Min Range: -9.1121
Max Act: 8.6121. Min Act: -0.1700
Data Index: 8717190 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1121. Min Range: -9.1121
Max Act: 8.5496. Min Act: -0.1700
Data Index: 8078615 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1121. Min Range: -9.1121
Max Act: 8.5496. Min Act: -0.1700
Data Index: 4304425 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1121. Min Range: -9.1121
Max Act: 8.5496. Min Act: -0.1700
Data Index: 2343142 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1121. Min Range: -9.1121
Max Act: 8.5496. Min Act: -0.1700
Data Index: 8167219 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1121. Min Range: -9.1121
Max Act: 8.4871. Min Act: -0.1700
Data Index: 8693366 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1121. Min Range: -9.1121
Max Act: 8.4871. Min Act: -0.1700
Data Index: 1656671 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1121. Min Range: -9.1121
Max Act: 8.4871. Min Act: -0.1700
Data Index: 496456 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1121. Min Range: -9.1121
Max Act: 8.4246. Min Act: -0.1700
Data Index: 64511 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1121. Min Range: -9.1121
Max Act: 8.4246. Min Act: -0.1700
Data Index: 5516140 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1121. Min Range: -9.1121
Max Act: 8.4246. Min Act: -0.1700
Data Index: 7037342 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1121. Min Range: -9.1121
Max Act: 8.4246. Min Act: -0.1700
Data Index: 4799567 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1121. Min Range: -9.1121
Max Act: 8.3621. Min Act: -0.1700
Data Index: 7351238 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #19