Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3066 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9516. Min Range: -8.9516
Max Act: 8.9516. Min Act: -0.1700
Data Index: 849813 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9516. Min Range: -8.9516
Max Act: 8.8891. Min Act: -0.1700
Data Index: 4048962 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9516. Min Range: -8.9516
Max Act: 8.7641. Min Act: -0.1700
Data Index: 6609011 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9516. Min Range: -8.9516
Max Act: 8.7641. Min Act: -0.1700
Data Index: 5843794 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9516. Min Range: -8.9516
Max Act: 8.6391. Min Act: -0.1700
Data Index: 857430 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9516. Min Range: -8.9516
Max Act: 8.5766. Min Act: -0.1700
Data Index: 3549065 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9516. Min Range: -8.9516
Max Act: 8.5766. Min Act: -0.1700
Data Index: 4766667 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9516. Min Range: -8.9516
Max Act: 8.4516. Min Act: -0.1700
Data Index: 7516633 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9516. Min Range: -8.9516
Max Act: 8.4516. Min Act: -0.1700
Data Index: 1379998 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9516. Min Range: -8.9516
Max Act: 8.3266. Min Act: -0.1700
Data Index: 6026771 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9516. Min Range: -8.9516
Max Act: 8.3266. Min Act: -0.1700
Data Index: 4659885 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9516. Min Range: -8.9516
Max Act: 8.2641. Min Act: -0.1700
Data Index: 1104307 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9516. Min Range: -8.9516
Max Act: 8.2016. Min Act: -0.1700
Data Index: 2668224 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9516. Min Range: -8.9516
Max Act: 8.1703. Min Act: -0.1700
Data Index: 8211139 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9516. Min Range: -8.9516
Max Act: 8.1703. Min Act: -0.1700
Data Index: 1190175 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9516. Min Range: -8.9516
Max Act: 8.0766. Min Act: -0.1700
Data Index: 3554738 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9516. Min Range: -8.9516
Max Act: 8.0453. Min Act: -0.1700
Data Index: 5780751 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9516. Min Range: -8.9516
Max Act: 8.0453. Min Act: -0.1700
Data Index: 3933499 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9516. Min Range: -8.9516
Max Act: 8.0453. Min Act: -0.1700
Data Index: 3467933 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9516. Min Range: -8.9516
Max Act: 7.9828. Min Act: -0.1700
Data Index: 1806377 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #19