Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2561 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3465. Min Range: -5.3465
Max Act: 5.3465. Min Act: -0.1700
Data Index: 1437018 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3465. Min Range: -5.3465
Max Act: 5.3152. Min Act: -0.1700
Data Index: 6373936 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3465. Min Range: -5.3465
Max Act: 5.2527. Min Act: -0.1698
Data Index: 1505964 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3465. Min Range: -5.3465
Max Act: 5.2527. Min Act: -0.1700
Data Index: 1443561 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3465. Min Range: -5.3465
Max Act: 5.2215. Min Act: -0.1700
Data Index: 7515602 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3465. Min Range: -5.3465
Max Act: 5.2215. Min Act: -0.1700
Data Index: 8637285 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3465. Min Range: -5.3465
Max Act: 5.1902. Min Act: -0.1700
Data Index: 6632386 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3465. Min Range: -5.3465
Max Act: 5.2215. Min Act: -0.1700
Data Index: 7146991 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3465. Min Range: -5.3465
Max Act: 5.1902. Min Act: -0.1700
Data Index: 3561834 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3465. Min Range: -5.3465
Max Act: 5.1902. Min Act: -0.1700
Data Index: 609828 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3465. Min Range: -5.3465
Max Act: 5.1590. Min Act: -0.1700
Data Index: 3656458 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3465. Min Range: -5.3465
Max Act: 5.1277. Min Act: -0.1700
Data Index: 4037102 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3465. Min Range: -5.3465
Max Act: 5.1277. Min Act: -0.1700
Data Index: 5015299 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3465. Min Range: -5.3465
Max Act: 5.1277. Min Act: -0.1700
Data Index: 7711416 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3465. Min Range: -5.3465
Max Act: 5.1277. Min Act: -0.1700
Data Index: 1207866 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3465. Min Range: -5.3465
Max Act: 5.1277. Min Act: -0.1700
Data Index: 4160506 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3465. Min Range: -5.3465
Max Act: 5.1277. Min Act: -0.1700
Data Index: 351635 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3465. Min Range: -5.3465
Max Act: 5.1277. Min Act: -0.1700
Data Index: 1532060 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3465. Min Range: -5.3465
Max Act: 5.0965. Min Act: -0.1700
Data Index: 5717347 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3465. Min Range: -5.3465
Max Act: 5.0965. Min Act: -0.1700
Data Index: 1090097 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #19