Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2987 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0579. Min Range: -5.0579
Max Act: 5.0579. Min Act: -0.1700
Data Index: 485274 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0579. Min Range: -5.0579
Max Act: 4.9954. Min Act: -0.1700
Data Index: 3893699 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0579. Min Range: -5.0579
Max Act: 4.9642. Min Act: -0.1700
Data Index: 8080092 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0579. Min Range: -5.0579
Max Act: 4.9017. Min Act: -0.1700
Data Index: 5533279 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0579. Min Range: -5.0579
Max Act: 4.9017. Min Act: -0.1700
Data Index: 177896 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0579. Min Range: -5.0579
Max Act: 4.8704. Min Act: -0.1700
Data Index: 4240943 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0579. Min Range: -5.0579
Max Act: 4.8079. Min Act: -0.1700
Data Index: 5256625 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0579. Min Range: -5.0579
Max Act: 4.7767. Min Act: -0.1700
Data Index: 1110451 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0579. Min Range: -5.0579
Max Act: 4.7767. Min Act: -0.1700
Data Index: 5228761 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0579. Min Range: -5.0579
Max Act: 4.7767. Min Act: -0.1700
Data Index: 2833135 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0579. Min Range: -5.0579
Max Act: 4.7142. Min Act: -0.1700
Data Index: 4089160 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0579. Min Range: -5.0579
Max Act: 4.7142. Min Act: -0.1700
Data Index: 7352412 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0579. Min Range: -5.0579
Max Act: 4.7142. Min Act: -0.1700
Data Index: 1184119 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0579. Min Range: -5.0579
Max Act: 4.7142. Min Act: -0.1700
Data Index: 6474173 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0579. Min Range: -5.0579
Max Act: 4.7142. Min Act: -0.1700
Data Index: 3147832 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0579. Min Range: -5.0579
Max Act: 4.6829. Min Act: -0.1700
Data Index: 5571463 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0579. Min Range: -5.0579
Max Act: 4.6829. Min Act: -0.1700
Data Index: 5757025 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0579. Min Range: -5.0579
Max Act: 4.6829. Min Act: -0.1700
Data Index: 5981049 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0579. Min Range: -5.0579
Max Act: 4.6829. Min Act: -0.1700
Data Index: 6474499 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0579. Min Range: -5.0579
Max Act: 4.6829. Min Act: -0.1700
Data Index: 702560 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #19