Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6361 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3587. Min Range: -6.3587
Max Act: 6.3587. Min Act: -0.1700
Data Index: 1381777 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3587. Min Range: -6.3587
Max Act: 6.2337. Min Act: -0.1700
Data Index: 8774619 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3587. Min Range: -6.3587
Max Act: 6.1712. Min Act: -0.1700
Data Index: 4805525 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3587. Min Range: -6.3587
Max Act: 6.1399. Min Act: -0.1700
Data Index: 7490444 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3587. Min Range: -6.3587
Max Act: 6.0149. Min Act: -0.1700
Data Index: 3869281 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3587. Min Range: -6.3587
Max Act: 6.0462. Min Act: -0.1700
Data Index: 492094 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3587. Min Range: -6.3587
Max Act: 6.0462. Min Act: -0.1700
Data Index: 4617554 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3587. Min Range: -6.3587
Max Act: 5.9837. Min Act: -0.1700
Data Index: 1610316 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3587. Min Range: -6.3587
Max Act: 5.9837. Min Act: -0.1700
Data Index: 2387382 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3587. Min Range: -6.3587
Max Act: 5.9837. Min Act: -0.1700
Data Index: 1551168 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3587. Min Range: -6.3587
Max Act: 5.9837. Min Act: -0.1700
Data Index: 8729029 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3587. Min Range: -6.3587
Max Act: 5.9837. Min Act: -0.1700
Data Index: 388111 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3587. Min Range: -6.3587
Max Act: 5.9524. Min Act: -0.1700
Data Index: 8134839 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3587. Min Range: -6.3587
Max Act: 6.0149. Min Act: -0.1700
Data Index: 3118731 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3587. Min Range: -6.3587
Max Act: 5.9837. Min Act: -0.1700
Data Index: 7600506 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3587. Min Range: -6.3587
Max Act: 5.9212. Min Act: -0.1700
Data Index: 2331591 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3587. Min Range: -6.3587
Max Act: 5.9212. Min Act: -0.1700
Data Index: 8731419 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3587. Min Range: -6.3587
Max Act: 5.9212. Min Act: -0.1700
Data Index: 2707222 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3587. Min Range: -6.3587
Max Act: 5.9212. Min Act: -0.1700
Data Index: 1518913 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3587. Min Range: -6.3587
Max Act: 5.8587. Min Act: -0.1700
Data Index: 3856274 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #19