Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6156 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8653. Min Range: -5.8653
Max Act: 5.8653. Min Act: -0.1700
Data Index: 2193456 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8653. Min Range: -5.8653
Max Act: 5.8028. Min Act: -0.1700
Data Index: 5208602 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8653. Min Range: -5.8653
Max Act: 5.7716. Min Act: -0.1700
Data Index: 7075499 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8653. Min Range: -5.8653
Max Act: 5.7716. Min Act: -0.1700
Data Index: 4611609 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8653. Min Range: -5.8653
Max Act: 5.7403. Min Act: -0.1700
Data Index: 752657 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8653. Min Range: -5.8653
Max Act: 5.7091. Min Act: -0.1700
Data Index: 6679673 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8653. Min Range: -5.8653
Max Act: 5.7403. Min Act: -0.1700
Data Index: 5376318 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8653. Min Range: -5.8653
Max Act: 5.7716. Min Act: -0.1700
Data Index: 3664600 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8653. Min Range: -5.8653
Max Act: 5.7091. Min Act: -0.1700
Data Index: 8638278 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8653. Min Range: -5.8653
Max Act: 5.6778. Min Act: -0.1700
Data Index: 4621653 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8653. Min Range: -5.8653
Max Act: 5.7091. Min Act: -0.1700
Data Index: 8071278 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8653. Min Range: -5.8653
Max Act: 5.7091. Min Act: -0.1700
Data Index: 3911340 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8653. Min Range: -5.8653
Max Act: 5.7091. Min Act: -0.1700
Data Index: 2356466 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8653. Min Range: -5.8653
Max Act: 5.7091. Min Act: -0.1700
Data Index: 3817359 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8653. Min Range: -5.8653
Max Act: 5.7091. Min Act: -0.1700
Data Index: 8321319 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8653. Min Range: -5.8653
Max Act: 5.7091. Min Act: -0.1699
Data Index: 5726025 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8653. Min Range: -5.8653
Max Act: 5.7091. Min Act: -0.1700
Data Index: 918469 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8653. Min Range: -5.8653
Max Act: 5.6778. Min Act: -0.1700
Data Index: 5952354 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8653. Min Range: -5.8653
Max Act: 5.6778. Min Act: -0.1700
Data Index: 6220170 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8653. Min Range: -5.8653
Max Act: 5.6778. Min Act: -0.1700
Data Index: 5467588 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #19