Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6244 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6970. Min Range: -8.6970
Max Act: 8.6970. Min Act: -0.1700
Data Index: 777591 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6970. Min Range: -8.6970
Max Act: 8.1970. Min Act: -0.1700
Data Index: 3012836 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6970. Min Range: -8.6970
Max Act: 8.1970. Min Act: -0.1700
Data Index: 4019566 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6970. Min Range: -8.6970
Max Act: 8.0720. Min Act: -0.1700
Data Index: 7254817 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6970. Min Range: -8.6970
Max Act: 8.0095. Min Act: -0.1700
Data Index: 1137315 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6970. Min Range: -8.6970
Max Act: 8.0095. Min Act: -0.1700
Data Index: 940389 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6970. Min Range: -8.6970
Max Act: 7.9470. Min Act: -0.1700
Data Index: 1679526 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6970. Min Range: -8.6970
Max Act: 7.9470. Min Act: -0.1700
Data Index: 6564116 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6970. Min Range: -8.6970
Max Act: 7.9470. Min Act: -0.1700
Data Index: 480787 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6970. Min Range: -8.6970
Max Act: 7.8220. Min Act: -0.1700
Data Index: 8128557 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6970. Min Range: -8.6970
Max Act: 7.8845. Min Act: -0.1700
Data Index: 7537538 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6970. Min Range: -8.6970
Max Act: 7.9470. Min Act: -0.1700
Data Index: 6623223 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6970. Min Range: -8.6970
Max Act: 7.9470. Min Act: -0.1700
Data Index: 4349424 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6970. Min Range: -8.6970
Max Act: 7.8845. Min Act: -0.1700
Data Index: 8695687 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6970. Min Range: -8.6970
Max Act: 7.8845. Min Act: -0.1700
Data Index: 396146 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6970. Min Range: -8.6970
Max Act: 7.8845. Min Act: -0.1700
Data Index: 1563982 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6970. Min Range: -8.6970
Max Act: 7.8845. Min Act: -0.1700
Data Index: 5038959 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6970. Min Range: -8.6970
Max Act: 7.8220. Min Act: -0.1700
Data Index: 7189536 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6970. Min Range: -8.6970
Max Act: 7.8220. Min Act: -0.1700
Data Index: 2050307 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6970. Min Range: -8.6970
Max Act: 7.8220. Min Act: -0.1700
Data Index: 7140967 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #19