Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3142 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9139. Min Range: -8.9139
Max Act: 8.9139. Min Act: -0.1700
Data Index: 3270458 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9139. Min Range: -8.9139
Max Act: 8.9139. Min Act: -0.1700
Data Index: 4659117 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9139. Min Range: -8.9139
Max Act: 8.4139. Min Act: -0.1700
Data Index: 982087 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9139. Min Range: -8.9139
Max Act: 8.4139. Min Act: -0.1700
Data Index: 6040126 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9139. Min Range: -8.9139
Max Act: 8.4139. Min Act: -0.1700
Data Index: 1357007 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9139. Min Range: -8.9139
Max Act: 8.4139. Min Act: -0.1700
Data Index: 6509308 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9139. Min Range: -8.9139
Max Act: 8.3514. Min Act: -0.1700
Data Index: 2126428 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9139. Min Range: -8.9139
Max Act: 8.3514. Min Act: -0.1700
Data Index: 3378501 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9139. Min Range: -8.9139
Max Act: 8.2889. Min Act: -0.1700
Data Index: 7891476 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9139. Min Range: -8.9139
Max Act: 8.2264. Min Act: -0.1700
Data Index: 3532051 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9139. Min Range: -8.9139
Max Act: 8.2264. Min Act: -0.1700
Data Index: 6099426 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9139. Min Range: -8.9139
Max Act: 8.2264. Min Act: -0.1700
Data Index: 4087244 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9139. Min Range: -8.9139
Max Act: 8.2264. Min Act: -0.1700
Data Index: 3434102 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9139. Min Range: -8.9139
Max Act: 8.0389. Min Act: -0.1700
Data Index: 8576950 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9139. Min Range: -8.9139
Max Act: 8.1014. Min Act: -0.1700
Data Index: 6264757 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9139. Min Range: -8.9139
Max Act: 8.1014. Min Act: -0.1700
Data Index: 8718798 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9139. Min Range: -8.9139
Max Act: 8.1014. Min Act: -0.1700
Data Index: 1145957 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9139. Min Range: -8.9139
Max Act: 8.1014. Min Act: -0.1700
Data Index: 3570816 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9139. Min Range: -8.9139
Max Act: 8.0389. Min Act: -0.1700
Data Index: 6290073 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9139. Min Range: -8.9139
Max Act: 7.9764. Min Act: -0.1700
Data Index: 6371635 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #19