Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6385 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0562. Min Range: -4.0562
Max Act: 4.0562. Min Act: -0.1700
Data Index: 2329961 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0562. Min Range: -4.0562
Max Act: 3.9937. Min Act: -0.1700
Data Index: 4251985 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0562. Min Range: -4.0562
Max Act: 4.0250. Min Act: -0.1700
Data Index: 1036615 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0562. Min Range: -4.0562
Max Act: 4.0250. Min Act: -0.1700
Data Index: 7478538 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0562. Min Range: -4.0562
Max Act: 3.9937. Min Act: -0.1700
Data Index: 781527 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0562. Min Range: -4.0562
Max Act: 3.9937. Min Act: -0.1700
Data Index: 1539490 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0562. Min Range: -4.0562
Max Act: 3.9312. Min Act: -0.1700
Data Index: 3530152 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0562. Min Range: -4.0562
Max Act: 3.9312. Min Act: -0.1700
Data Index: 6088988 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0562. Min Range: -4.0562
Max Act: 3.8999. Min Act: -0.1700
Data Index: 6357139 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0562. Min Range: -4.0562
Max Act: 3.8999. Min Act: -0.1700
Data Index: 168325 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0562. Min Range: -4.0562
Max Act: 3.8686. Min Act: -0.1700
Data Index: 7785376 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0562. Min Range: -4.0562
Max Act: 3.8374. Min Act: -0.1700
Data Index: 5937069 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0562. Min Range: -4.0562
Max Act: 3.8686. Min Act: -0.1700
Data Index: 4064424 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0562. Min Range: -4.0562
Max Act: 3.8686. Min Act: -0.1700
Data Index: 5528131 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0562. Min Range: -4.0562
Max Act: 3.8686. Min Act: -0.1700
Data Index: 5020752 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0562. Min Range: -4.0562
Max Act: 3.8374. Min Act: -0.1700
Data Index: 1920535 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0562. Min Range: -4.0562
Max Act: 3.8374. Min Act: -0.1700
Data Index: 198765 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0562. Min Range: -4.0562
Max Act: 3.8374. Min Act: -0.1700
Data Index: 2730576 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0562. Min Range: -4.0562
Max Act: 3.8061. Min Act: -0.1700
Data Index: 6467014 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0562. Min Range: -4.0562
Max Act: 3.8374. Min Act: -0.1700
Data Index: 1843746 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #19