Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4820 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6720. Min Range: -7.6720
Max Act: 7.6720. Min Act: -0.1700
Data Index: 4484008 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6720. Min Range: -7.6720
Max Act: 7.5158. Min Act: -0.1700
Data Index: 2277495 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6720. Min Range: -7.6720
Max Act: 7.3283. Min Act: -0.1700
Data Index: 7849594 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6720. Min Range: -7.6720
Max Act: 7.2345. Min Act: -0.1700
Data Index: 1200440 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6720. Min Range: -7.6720
Max Act: 7.1720. Min Act: -0.1700
Data Index: 3930544 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6720. Min Range: -7.6720
Max Act: 7.1720. Min Act: -0.1700
Data Index: 539295 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6720. Min Range: -7.6720
Max Act: 7.1408. Min Act: -0.1700
Data Index: 3378907 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6720. Min Range: -7.6720
Max Act: 7.1095. Min Act: -0.1700
Data Index: 8313803 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6720. Min Range: -7.6720
Max Act: 7.0783. Min Act: -0.1700
Data Index: 6462154 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6720. Min Range: -7.6720
Max Act: 7.1095. Min Act: -0.1700
Data Index: 5145701 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6720. Min Range: -7.6720
Max Act: 7.0470. Min Act: -0.1700
Data Index: 7026439 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6720. Min Range: -7.6720
Max Act: 7.0470. Min Act: -0.1700
Data Index: 2239828 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6720. Min Range: -7.6720
Max Act: 7.0470. Min Act: -0.1700
Data Index: 2086273 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6720. Min Range: -7.6720
Max Act: 7.0470. Min Act: -0.1700
Data Index: 8311575 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6720. Min Range: -7.6720
Max Act: 7.0158. Min Act: -0.1700
Data Index: 1751004 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6720. Min Range: -7.6720
Max Act: 7.0470. Min Act: -0.1700
Data Index: 4740537 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6720. Min Range: -7.6720
Max Act: 7.0158. Min Act: -0.1700
Data Index: 824079 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6720. Min Range: -7.6720
Max Act: 7.0158. Min Act: -0.1700
Data Index: 354675 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6720. Min Range: -7.6720
Max Act: 6.9845. Min Act: -0.1700
Data Index: 7081192 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6720. Min Range: -7.6720
Max Act: 6.9845. Min Act: -0.1700
Data Index: 6348864 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #19