Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6377 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7747. Min Range: -5.7747
Max Act: 5.7747. Min Act: -0.1700
Data Index: 5920856 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7747. Min Range: -5.7747
Max Act: 5.4935. Min Act: -0.1700
Data Index: 6244113 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7747. Min Range: -5.7747
Max Act: 5.4310. Min Act: -0.1700
Data Index: 7150205 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7747. Min Range: -5.7747
Max Act: 5.3372. Min Act: -0.1700
Data Index: 6246255 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7747. Min Range: -5.7747
Max Act: 5.3060. Min Act: -0.1700
Data Index: 5988666 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7747. Min Range: -5.7747
Max Act: 5.2747. Min Act: -0.1700
Data Index: 717364 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7747. Min Range: -5.7747
Max Act: 5.2122. Min Act: -0.1700
Data Index: 3633179 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7747. Min Range: -5.7747
Max Act: 5.2435. Min Act: -0.1700
Data Index: 1017645 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7747. Min Range: -5.7747
Max Act: 5.2435. Min Act: -0.1700
Data Index: 6980110 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7747. Min Range: -5.7747
Max Act: 5.2122. Min Act: -0.1700
Data Index: 5434521 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7747. Min Range: -5.7747
Max Act: 5.2122. Min Act: -0.1700
Data Index: 6371747 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7747. Min Range: -5.7747
Max Act: 5.2747. Min Act: -0.1700
Data Index: 731058 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7747. Min Range: -5.7747
Max Act: 5.1810. Min Act: -0.1700
Data Index: 5353590 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7747. Min Range: -5.7747
Max Act: 5.1497. Min Act: -0.1700
Data Index: 5648363 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7747. Min Range: -5.7747
Max Act: 5.1810. Min Act: -0.1700
Data Index: 2775486 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7747. Min Range: -5.7747
Max Act: 5.1185. Min Act: -0.1700
Data Index: 6611326 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7747. Min Range: -5.7747
Max Act: 5.0872. Min Act: -0.1700
Data Index: 5894756 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7747. Min Range: -5.7747
Max Act: 5.1185. Min Act: -0.1700
Data Index: 5014097 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7747. Min Range: -5.7747
Max Act: 5.0872. Min Act: -0.1700
Data Index: 5672540 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7747. Min Range: -5.7747
Max Act: 5.0560. Min Act: -0.1700
Data Index: 841302 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #19