Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4393 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2831. Min Range: -8.2831
Max Act: 8.2831. Min Act: -0.1700
Data Index: 562856 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2831. Min Range: -8.2831
Max Act: 8.2519. Min Act: -0.1700
Data Index: 8702875 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2831. Min Range: -8.2831
Max Act: 8.2206. Min Act: -0.1700
Data Index: 3715136 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2831. Min Range: -8.2831
Max Act: 8.0644. Min Act: -0.1700
Data Index: 1374605 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2831. Min Range: -8.2831
Max Act: 7.9394. Min Act: -0.1700
Data Index: 6495763 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2831. Min Range: -8.2831
Max Act: 7.9394. Min Act: -0.1700
Data Index: 8010652 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2831. Min Range: -8.2831
Max Act: 7.8769. Min Act: -0.1700
Data Index: 6538071 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2831. Min Range: -8.2831
Max Act: 7.7831. Min Act: -0.1700
Data Index: 3947060 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2831. Min Range: -8.2831
Max Act: 7.7831. Min Act: -0.1700
Data Index: 926086 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2831. Min Range: -8.2831
Max Act: 7.7206. Min Act: -0.1700
Data Index: 8092459 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2831. Min Range: -8.2831
Max Act: 7.6894. Min Act: -0.1700
Data Index: 4790526 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2831. Min Range: -8.2831
Max Act: 7.6269. Min Act: -0.1700
Data Index: 3315476 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2831. Min Range: -8.2831
Max Act: 7.5956. Min Act: -0.1700
Data Index: 2603086 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2831. Min Range: -8.2831
Max Act: 7.5644. Min Act: -0.1700
Data Index: 5488699 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2831. Min Range: -8.2831
Max Act: 7.5956. Min Act: -0.1700
Data Index: 6081633 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2831. Min Range: -8.2831
Max Act: 7.5331. Min Act: -0.1700
Data Index: 3261411 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2831. Min Range: -8.2831
Max Act: 7.5019. Min Act: -0.1700
Data Index: 6785499 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2831. Min Range: -8.2831
Max Act: 7.4706. Min Act: -0.1700
Data Index: 7076562 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2831. Min Range: -8.2831
Max Act: 7.4706. Min Act: -0.1700
Data Index: 8452221 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2831. Min Range: -8.2831
Max Act: 7.4706. Min Act: -0.1700
Data Index: 5785025 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #19