Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5530 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5477. Min Range: -7.5477
Max Act: 7.5477. Min Act: -0.1700
Data Index: 6868901 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5477. Min Range: -7.5477
Max Act: 7.5477. Min Act: -0.1700
Data Index: 5222955 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5477. Min Range: -7.5477
Max Act: 7.4539. Min Act: -0.1700
Data Index: 7996336 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5477. Min Range: -7.5477
Max Act: 7.3914. Min Act: -0.1700
Data Index: 7251196 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5477. Min Range: -7.5477
Max Act: 7.4539. Min Act: -0.1700
Data Index: 7489165 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5477. Min Range: -7.5477
Max Act: 7.3602. Min Act: -0.1700
Data Index: 344561 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5477. Min Range: -7.5477
Max Act: 7.3289. Min Act: -0.1700
Data Index: 5903360 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5477. Min Range: -7.5477
Max Act: 7.2664. Min Act: -0.1700
Data Index: 8320673 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5477. Min Range: -7.5477
Max Act: 7.2352. Min Act: -0.1700
Data Index: 2821306 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5477. Min Range: -7.5477
Max Act: 7.2039. Min Act: -0.1700
Data Index: 7052576 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5477. Min Range: -7.5477
Max Act: 7.1727. Min Act: -0.1700
Data Index: 6497538 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5477. Min Range: -7.5477
Max Act: 7.1727. Min Act: -0.1700
Data Index: 1160562 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5477. Min Range: -7.5477
Max Act: 7.0789. Min Act: -0.1700
Data Index: 7595304 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5477. Min Range: -7.5477
Max Act: 7.0164. Min Act: -0.1700
Data Index: 2297296 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5477. Min Range: -7.5477
Max Act: 7.0477. Min Act: -0.1700
Data Index: 4796385 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5477. Min Range: -7.5477
Max Act: 6.9852. Min Act: -0.1700
Data Index: 1930385 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5477. Min Range: -7.5477
Max Act: 6.9227. Min Act: -0.1700
Data Index: 5401152 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5477. Min Range: -7.5477
Max Act: 6.8602. Min Act: -0.1700
Data Index: 2015026 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5477. Min Range: -7.5477
Max Act: 6.8914. Min Act: -0.1700
Data Index: 2533849 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5477. Min Range: -7.5477
Max Act: 6.8602. Min Act: -0.1700
Data Index: 1160561 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #19