Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1080 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0775. Min Range: -5.0775
Max Act: 5.0775. Min Act: -0.1700
Data Index: 6945619 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0775. Min Range: -5.0775
Max Act: 5.0463. Min Act: -0.1700
Data Index: 5431377 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0775. Min Range: -5.0775
Max Act: 5.0150. Min Act: -0.1700
Data Index: 1869532 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0775. Min Range: -5.0775
Max Act: 5.0150. Min Act: -0.1700
Data Index: 882718 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0775. Min Range: -5.0775
Max Act: 4.9838. Min Act: -0.1700
Data Index: 7746219 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0775. Min Range: -5.0775
Max Act: 4.9838. Min Act: -0.1700
Data Index: 1134274 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0775. Min Range: -5.0775
Max Act: 4.9838. Min Act: -0.1700
Data Index: 2878780 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0775. Min Range: -5.0775
Max Act: 4.9838. Min Act: -0.1700
Data Index: 1450052 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0775. Min Range: -5.0775
Max Act: 4.9838. Min Act: -0.1700
Data Index: 701357 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0775. Min Range: -5.0775
Max Act: 4.9525. Min Act: -0.1700
Data Index: 3573856 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0775. Min Range: -5.0775
Max Act: 4.9525. Min Act: -0.1700
Data Index: 5690309 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0775. Min Range: -5.0775
Max Act: 4.9525. Min Act: -0.1700
Data Index: 7719074 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0775. Min Range: -5.0775
Max Act: 4.9213. Min Act: -0.1700
Data Index: 2396427 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0775. Min Range: -5.0775
Max Act: 4.9213. Min Act: -0.1700
Data Index: 4282692 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0775. Min Range: -5.0775
Max Act: 4.9213. Min Act: -0.1700
Data Index: 3975581 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0775. Min Range: -5.0775
Max Act: 4.9213. Min Act: -0.1700
Data Index: 965639 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0775. Min Range: -5.0775
Max Act: 4.9213. Min Act: -0.1700
Data Index: 2868696 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0775. Min Range: -5.0775
Max Act: 4.9213. Min Act: -0.1700
Data Index: 3906495 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0775. Min Range: -5.0775
Max Act: 4.9213. Min Act: -0.1700
Data Index: 2771530 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0775. Min Range: -5.0775
Max Act: 4.8900. Min Act: -0.1700
Data Index: 6892599 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #19