Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4396 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1588. Min Range: -4.1588
Max Act: 4.1588. Min Act: -0.1700
Data Index: 4875978 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1588. Min Range: -4.1588
Max Act: 4.1275. Min Act: -0.1700
Data Index: 5460662 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1588. Min Range: -4.1588
Max Act: 4.0025. Min Act: -0.1700
Data Index: 5483616 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1588. Min Range: -4.1588
Max Act: 4.0025. Min Act: -0.1700
Data Index: 3192608 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1588. Min Range: -4.1588
Max Act: 3.9712. Min Act: -0.1700
Data Index: 7662583 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1588. Min Range: -4.1588
Max Act: 3.9712. Min Act: -0.1700
Data Index: 4385861 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1588. Min Range: -4.1588
Max Act: 3.9712. Min Act: -0.1700
Data Index: 1157896 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1588. Min Range: -4.1588
Max Act: 3.9712. Min Act: -0.1700
Data Index: 5686527 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1588. Min Range: -4.1588
Max Act: 3.9400. Min Act: -0.1700
Data Index: 6891875 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1588. Min Range: -4.1588
Max Act: 3.9400. Min Act: -0.1700
Data Index: 7265905 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1588. Min Range: -4.1588
Max Act: 3.9400. Min Act: -0.1700
Data Index: 3005070 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1588. Min Range: -4.1588
Max Act: 3.9087. Min Act: -0.1700
Data Index: 4374823 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1588. Min Range: -4.1588
Max Act: 3.9087. Min Act: -0.1700
Data Index: 2380482 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1588. Min Range: -4.1588
Max Act: 3.8774. Min Act: -0.1700
Data Index: 396258 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1588. Min Range: -4.1588
Max Act: 3.9087. Min Act: -0.1700
Data Index: 4410073 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1588. Min Range: -4.1588
Max Act: 3.8149. Min Act: -0.1700
Data Index: 1962291 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1588. Min Range: -4.1588
Max Act: 3.8149. Min Act: -0.1700
Data Index: 5334438 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1588. Min Range: -4.1588
Max Act: 3.7836. Min Act: -0.1700
Data Index: 1388889 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1588. Min Range: -4.1588
Max Act: 3.7836. Min Act: -0.1700
Data Index: 7727582 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1588. Min Range: -4.1588
Max Act: 3.7836. Min Act: -0.1700
Data Index: 8527867 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #19