Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1334 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3338. Min Range: -8.3338
Max Act: 8.3338. Min Act: -0.1700
Data Index: 3466135 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3338. Min Range: -8.3338
Max Act: 8.2088. Min Act: -0.1700
Data Index: 4712231 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3338. Min Range: -8.3338
Max Act: 8.2088. Min Act: -0.1700
Data Index: 8100300 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3338. Min Range: -8.3338
Max Act: 8.0838. Min Act: -0.1700
Data Index: 2816901 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3338. Min Range: -8.3338
Max Act: 8.0213. Min Act: -0.1700
Data Index: 5549227 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3338. Min Range: -8.3338
Max Act: 8.0838. Min Act: -0.1700
Data Index: 1060318 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3338. Min Range: -8.3338
Max Act: 8.0213. Min Act: -0.1700
Data Index: 2716112 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3338. Min Range: -8.3338
Max Act: 8.0213. Min Act: -0.1700
Data Index: 4516678 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3338. Min Range: -8.3338
Max Act: 7.9588. Min Act: -0.1700
Data Index: 2794372 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3338. Min Range: -8.3338
Max Act: 7.9588. Min Act: -0.1700
Data Index: 941722 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3338. Min Range: -8.3338
Max Act: 7.9588. Min Act: -0.1700
Data Index: 4640425 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3338. Min Range: -8.3338
Max Act: 7.8963. Min Act: -0.1700
Data Index: 8037299 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3338. Min Range: -8.3338
Max Act: 7.8963. Min Act: -0.1700
Data Index: 1138574 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3338. Min Range: -8.3338
Max Act: 7.8963. Min Act: -0.1700
Data Index: 255103 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3338. Min Range: -8.3338
Max Act: 7.8963. Min Act: -0.1700
Data Index: 3078416 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3338. Min Range: -8.3338
Max Act: 7.8963. Min Act: -0.1700
Data Index: 7957464 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3338. Min Range: -8.3338
Max Act: 7.8963. Min Act: -0.1700
Data Index: 3359417 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3338. Min Range: -8.3338
Max Act: 7.8963. Min Act: -0.1700
Data Index: 5601524 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3338. Min Range: -8.3338
Max Act: 7.8338. Min Act: -0.1700
Data Index: 2856588 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3338. Min Range: -8.3338
Max Act: 7.8338. Min Act: -0.1700
Data Index: 4075243 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #19