Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2728 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7284. Min Range: -7.7284
Max Act: 7.7284. Min Act: -0.1700
Data Index: 66405 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7284. Min Range: -7.7284
Max Act: 7.4784. Min Act: -0.1700
Data Index: 1442596 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7284. Min Range: -7.7284
Max Act: 7.4159. Min Act: -0.1700
Data Index: 6503072 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7284. Min Range: -7.7284
Max Act: 7.2284. Min Act: -0.1700
Data Index: 6577729 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7284. Min Range: -7.7284
Max Act: 7.1971. Min Act: -0.1700
Data Index: 8525723 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7284. Min Range: -7.7284
Max Act: 7.1659. Min Act: -0.1700
Data Index: 7931445 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7284. Min Range: -7.7284
Max Act: 7.1346. Min Act: -0.1700
Data Index: 7347518 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7284. Min Range: -7.7284
Max Act: 7.1034. Min Act: -0.1700
Data Index: 5941859 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7284. Min Range: -7.7284
Max Act: 7.0721. Min Act: -0.1700
Data Index: 2642650 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7284. Min Range: -7.7284
Max Act: 7.0409. Min Act: -0.1700
Data Index: 5897710 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7284. Min Range: -7.7284
Max Act: 6.9784. Min Act: -0.1700
Data Index: 8037264 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7284. Min Range: -7.7284
Max Act: 7.0096. Min Act: -0.1700
Data Index: 3774134 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7284. Min Range: -7.7284
Max Act: 6.9471. Min Act: -0.1700
Data Index: 3785376 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7284. Min Range: -7.7284
Max Act: 7.0096. Min Act: -0.1700
Data Index: 2105460 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7284. Min Range: -7.7284
Max Act: 6.9471. Min Act: -0.1700
Data Index: 773250 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7284. Min Range: -7.7284
Max Act: 6.9471. Min Act: -0.1700
Data Index: 5370216 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7284. Min Range: -7.7284
Max Act: 6.9471. Min Act: -0.1700
Data Index: 8808290 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7284. Min Range: -7.7284
Max Act: 6.8534. Min Act: -0.1700
Data Index: 2548792 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7284. Min Range: -7.7284
Max Act: 6.8846. Min Act: -0.1700
Data Index: 8727802 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7284. Min Range: -7.7284
Max Act: 6.8846. Min Act: -0.1700
Data Index: 2580861 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #19