Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3492 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3259. Min Range: -6.3259
Max Act: 6.3259. Min Act: -0.1700
Data Index: 8701701 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3259. Min Range: -6.3259
Max Act: 6.2322. Min Act: -0.1700
Data Index: 7748715 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3259. Min Range: -6.3259
Max Act: 6.1697. Min Act: -0.1700
Data Index: 5369293 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3259. Min Range: -6.3259
Max Act: 6.1384. Min Act: -0.1700
Data Index: 5561367 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3259. Min Range: -6.3259
Max Act: 6.1072. Min Act: -0.1700
Data Index: 8031089 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3259. Min Range: -6.3259
Max Act: 6.0759. Min Act: -0.1700
Data Index: 5072280 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3259. Min Range: -6.3259
Max Act: 6.0447. Min Act: -0.1700
Data Index: 6164294 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3259. Min Range: -6.3259
Max Act: 6.0134. Min Act: -0.1700
Data Index: 8640953 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3259. Min Range: -6.3259
Max Act: 5.9509. Min Act: -0.1700
Data Index: 1966436 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3259. Min Range: -6.3259
Max Act: 5.9509. Min Act: -0.1700
Data Index: 3549584 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3259. Min Range: -6.3259
Max Act: 5.9509. Min Act: -0.1700
Data Index: 7896409 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3259. Min Range: -6.3259
Max Act: 5.8884. Min Act: -0.1700
Data Index: 223508 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3259. Min Range: -6.3259
Max Act: 5.8572. Min Act: -0.1700
Data Index: 5943510 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3259. Min Range: -6.3259
Max Act: 5.8259. Min Act: -0.1700
Data Index: 1917684 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3259. Min Range: -6.3259
Max Act: 5.8259. Min Act: -0.1700
Data Index: 4837808 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3259. Min Range: -6.3259
Max Act: 5.8572. Min Act: -0.1700
Data Index: 7443666 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3259. Min Range: -6.3259
Max Act: 5.8572. Min Act: -0.1700
Data Index: 786696 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3259. Min Range: -6.3259
Max Act: 5.8572. Min Act: -0.1700
Data Index: 454715 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3259. Min Range: -6.3259
Max Act: 5.8259. Min Act: -0.1700
Data Index: 8279527 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3259. Min Range: -6.3259
Max Act: 5.7634. Min Act: -0.1700
Data Index: 1980639 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #19