Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4433 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4139. Min Range: -6.4139
Max Act: 6.4139. Min Act: -0.1700
Data Index: 325025 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4139. Min Range: -6.4139
Max Act: 6.2577. Min Act: -0.1700
Data Index: 5454782 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4139. Min Range: -6.4139
Max Act: 6.2264. Min Act: -0.1700
Data Index: 366142 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4139. Min Range: -6.4139
Max Act: 6.1639. Min Act: -0.1700
Data Index: 1538764 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4139. Min Range: -6.4139
Max Act: 6.1639. Min Act: -0.1700
Data Index: 4213086 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4139. Min Range: -6.4139
Max Act: 6.1639. Min Act: -0.1700
Data Index: 3563478 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4139. Min Range: -6.4139
Max Act: 6.1327. Min Act: -0.1700
Data Index: 259779 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4139. Min Range: -6.4139
Max Act: 6.1014. Min Act: -0.1700
Data Index: 7465642 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4139. Min Range: -6.4139
Max Act: 6.0702. Min Act: -0.1700
Data Index: 2315781 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4139. Min Range: -6.4139
Max Act: 5.9764. Min Act: -0.1700
Data Index: 1511808 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4139. Min Range: -6.4139
Max Act: 5.9764. Min Act: -0.1700
Data Index: 1112254 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4139. Min Range: -6.4139
Max Act: 5.9764. Min Act: -0.1700
Data Index: 6880976 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4139. Min Range: -6.4139
Max Act: 5.9452. Min Act: -0.1700
Data Index: 7102685 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4139. Min Range: -6.4139
Max Act: 5.9452. Min Act: -0.1700
Data Index: 3562739 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4139. Min Range: -6.4139
Max Act: 5.9452. Min Act: -0.1700
Data Index: 5939981 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4139. Min Range: -6.4139
Max Act: 5.9452. Min Act: -0.1700
Data Index: 10331 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4139. Min Range: -6.4139
Max Act: 5.9452. Min Act: -0.1700
Data Index: 5800521 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4139. Min Range: -6.4139
Max Act: 5.8827. Min Act: -0.1700
Data Index: 2702753 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4139. Min Range: -6.4139
Max Act: 5.9139. Min Act: -0.1700
Data Index: 7102689 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4139. Min Range: -6.4139
Max Act: 5.8827. Min Act: -0.1700
Data Index: 1519366 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #19