Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2859 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.8357. Min Range: -9.8357
Max Act: 9.8357. Min Act: -0.1700
Data Index: 7859357 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.8357. Min Range: -9.8357
Max Act: 9.6482. Min Act: -0.1700
Data Index: 1299802 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.8357. Min Range: -9.8357
Max Act: 9.0232. Min Act: -0.1700
Data Index: 5324762 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.8357. Min Range: -9.8357
Max Act: 9.0232. Min Act: -0.1700
Data Index: 495854 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.8357. Min Range: -9.8357
Max Act: 9.0232. Min Act: -0.1700
Data Index: 4514879 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.8357. Min Range: -9.8357
Max Act: 8.9607. Min Act: -0.1700
Data Index: 5803118 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.8357. Min Range: -9.8357
Max Act: 8.8982. Min Act: -0.1700
Data Index: 817826 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.8357. Min Range: -9.8357
Max Act: 8.8357. Min Act: -0.1700
Data Index: 6257561 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.8357. Min Range: -9.8357
Max Act: 8.7732. Min Act: -0.1700
Data Index: 138825 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.8357. Min Range: -9.8357
Max Act: 8.7732. Min Act: -0.1700
Data Index: 7872763 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.8357. Min Range: -9.8357
Max Act: 8.7107. Min Act: -0.1700
Data Index: 5489928 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.8357. Min Range: -9.8357
Max Act: 8.7107. Min Act: -0.1700
Data Index: 8592236 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.8357. Min Range: -9.8357
Max Act: 8.7107. Min Act: -0.1700
Data Index: 8094850 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.8357. Min Range: -9.8357
Max Act: 8.7107. Min Act: -0.1700
Data Index: 4268544 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.8357. Min Range: -9.8357
Max Act: 8.7107. Min Act: -0.1700
Data Index: 6183742 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.8357. Min Range: -9.8357
Max Act: 8.6482. Min Act: -0.1700
Data Index: 1501033 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.8357. Min Range: -9.8357
Max Act: 8.6482. Min Act: -0.1700
Data Index: 7237428 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.8357. Min Range: -9.8357
Max Act: 8.6482. Min Act: -0.1700
Data Index: 945649 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.8357. Min Range: -9.8357
Max Act: 8.5857. Min Act: -0.1700
Data Index: 915308 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.8357. Min Range: -9.8357
Max Act: 8.6482. Min Act: -0.1700
Data Index: 8751253 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #19