Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3710 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0267. Min Range: -5.0267
Max Act: 4.9954. Min Act: -0.1700
Data Index: 1443453 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0267. Min Range: -5.0267
Max Act: 4.9954. Min Act: -0.1700
Data Index: 2648329 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0267. Min Range: -5.0267
Max Act: 5.0267. Min Act: -0.1700
Data Index: 4358789 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0267. Min Range: -5.0267
Max Act: 4.9017. Min Act: -0.1700
Data Index: 1866757 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0267. Min Range: -5.0267
Max Act: 4.8704. Min Act: -0.1700
Data Index: 6424493 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0267. Min Range: -5.0267
Max Act: 4.8392. Min Act: -0.1700
Data Index: 4342708 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0267. Min Range: -5.0267
Max Act: 4.8392. Min Act: -0.1700
Data Index: 6201124 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0267. Min Range: -5.0267
Max Act: 4.8079. Min Act: -0.1700
Data Index: 5599723 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0267. Min Range: -5.0267
Max Act: 4.7767. Min Act: -0.1700
Data Index: 751138 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0267. Min Range: -5.0267
Max Act: 4.7767. Min Act: -0.1700
Data Index: 2490350 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0267. Min Range: -5.0267
Max Act: 4.7767. Min Act: -0.1700
Data Index: 751135 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0267. Min Range: -5.0267
Max Act: 4.7454. Min Act: -0.1700
Data Index: 8540018 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0267. Min Range: -5.0267
Max Act: 4.7767. Min Act: -0.1700
Data Index: 3176141 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0267. Min Range: -5.0267
Max Act: 4.7454. Min Act: -0.1700
Data Index: 2523916 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0267. Min Range: -5.0267
Max Act: 4.7454. Min Act: -0.1700
Data Index: 7886926 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0267. Min Range: -5.0267
Max Act: 4.7454. Min Act: -0.1700
Data Index: 1191587 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0267. Min Range: -5.0267
Max Act: 4.7142. Min Act: -0.1700
Data Index: 8192720 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0267. Min Range: -5.0267
Max Act: 4.7142. Min Act: -0.1700
Data Index: 1907349 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0267. Min Range: -5.0267
Max Act: 4.6829. Min Act: -0.1700
Data Index: 1597217 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0267. Min Range: -5.0267
Max Act: 4.6829. Min Act: -0.1700
Data Index: 6424491 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #19