Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2868 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9519. Min Range: -8.9519
Max Act: 8.9519. Min Act: -0.1700
Data Index: 2372669 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9519. Min Range: -8.9519
Max Act: 8.8269. Min Act: -0.1700
Data Index: 7192227 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9519. Min Range: -8.9519
Max Act: 8.8269. Min Act: -0.1700
Data Index: 8616205 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9519. Min Range: -8.9519
Max Act: 8.7644. Min Act: -0.1700
Data Index: 6539905 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9519. Min Range: -8.9519
Max Act: 8.7644. Min Act: -0.1700
Data Index: 984870 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9519. Min Range: -8.9519
Max Act: 8.7644. Min Act: -0.1700
Data Index: 1451167 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9519. Min Range: -8.9519
Max Act: 8.7019. Min Act: -0.1700
Data Index: 579052 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9519. Min Range: -8.9519
Max Act: 8.7019. Min Act: -0.1700
Data Index: 6852393 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9519. Min Range: -8.9519
Max Act: 8.7019. Min Act: -0.1700
Data Index: 7009376 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9519. Min Range: -8.9519
Max Act: 8.7019. Min Act: -0.1700
Data Index: 2003388 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9519. Min Range: -8.9519
Max Act: 8.6394. Min Act: -0.1700
Data Index: 5394147 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9519. Min Range: -8.9519
Max Act: 8.6394. Min Act: -0.1700
Data Index: 5416116 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9519. Min Range: -8.9519
Max Act: 8.6394. Min Act: -0.1700
Data Index: 2485524 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9519. Min Range: -8.9519
Max Act: 8.5769. Min Act: -0.1700
Data Index: 1892184 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9519. Min Range: -8.9519
Max Act: 8.5144. Min Act: -0.1700
Data Index: 5572040 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9519. Min Range: -8.9519
Max Act: 8.5769. Min Act: -0.1700
Data Index: 1719517 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9519. Min Range: -8.9519
Max Act: 8.5769. Min Act: -0.1700
Data Index: 5541987 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9519. Min Range: -8.9519
Max Act: 8.5144. Min Act: -0.1700
Data Index: 3995373 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9519. Min Range: -8.9519
Max Act: 8.5144. Min Act: -0.1700
Data Index: 6759369 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9519. Min Range: -8.9519
Max Act: 8.4519. Min Act: -0.1700
Data Index: 6460644 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #19