Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2699 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8504. Min Range: -8.8504
Max Act: 8.8504. Min Act: -0.1700
Data Index: 6427537 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8504. Min Range: -8.8504
Max Act: 8.7879. Min Act: -0.1700
Data Index: 6791399 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8504. Min Range: -8.8504
Max Act: 8.4754. Min Act: -0.1700
Data Index: 106000 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8504. Min Range: -8.8504
Max Act: 8.4754. Min Act: -0.1700
Data Index: 6324279 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8504. Min Range: -8.8504
Max Act: 8.4754. Min Act: -0.1700
Data Index: 5662344 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8504. Min Range: -8.8504
Max Act: 8.3192. Min Act: -0.1700
Data Index: 809006 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8504. Min Range: -8.8504
Max Act: 8.2254. Min Act: -0.1700
Data Index: 3234407 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8504. Min Range: -8.8504
Max Act: 8.2254. Min Act: -0.1700
Data Index: 5167765 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8504. Min Range: -8.8504
Max Act: 8.2254. Min Act: -0.1700
Data Index: 2542162 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8504. Min Range: -8.8504
Max Act: 8.1942. Min Act: -0.1700
Data Index: 808998 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8504. Min Range: -8.8504
Max Act: 8.1629. Min Act: -0.1700
Data Index: 5500414 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8504. Min Range: -8.8504
Max Act: 8.0692. Min Act: -0.1700
Data Index: 3710787 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8504. Min Range: -8.8504
Max Act: 8.0379. Min Act: -0.1700
Data Index: 858626 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8504. Min Range: -8.8504
Max Act: 8.0067. Min Act: -0.1700
Data Index: 191732 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8504. Min Range: -8.8504
Max Act: 8.0067. Min Act: -0.1700
Data Index: 706358 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8504. Min Range: -8.8504
Max Act: 8.0067. Min Act: -0.1700
Data Index: 5136313 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8504. Min Range: -8.8504
Max Act: 7.9442. Min Act: -0.1700
Data Index: 195471 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8504. Min Range: -8.8504
Max Act: 7.9754. Min Act: -0.1700
Data Index: 8421758 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8504. Min Range: -8.8504
Max Act: 7.9129. Min Act: -0.1700
Data Index: 6723971 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8504. Min Range: -8.8504
Max Act: 7.8817. Min Act: -0.1700
Data Index: 2822265 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #19