Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4317 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2139. Min Range: -8.2139
Max Act: 8.2139. Min Act: -0.1700
Data Index: 605614 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2139. Min Range: -8.2139
Max Act: 8.1514. Min Act: -0.1700
Data Index: 6856573 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2139. Min Range: -8.2139
Max Act: 8.0889. Min Act: -0.1700
Data Index: 889867 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2139. Min Range: -8.2139
Max Act: 8.0889. Min Act: -0.1700
Data Index: 72353 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2139. Min Range: -8.2139
Max Act: 8.0264. Min Act: -0.1700
Data Index: 2287130 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2139. Min Range: -8.2139
Max Act: 8.0264. Min Act: -0.1700
Data Index: 6279002 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2139. Min Range: -8.2139
Max Act: 7.9639. Min Act: -0.1700
Data Index: 1707710 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2139. Min Range: -8.2139
Max Act: 7.9014. Min Act: -0.1700
Data Index: 7331698 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2139. Min Range: -8.2139
Max Act: 7.9014. Min Act: -0.1700
Data Index: 2323880 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2139. Min Range: -8.2139
Max Act: 7.8389. Min Act: -0.1700
Data Index: 7524681 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2139. Min Range: -8.2139
Max Act: 7.8389. Min Act: -0.1700
Data Index: 6450982 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2139. Min Range: -8.2139
Max Act: 7.7764. Min Act: -0.1700
Data Index: 3120714 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2139. Min Range: -8.2139
Max Act: 7.7764. Min Act: -0.1700
Data Index: 6233231 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2139. Min Range: -8.2139
Max Act: 7.7764. Min Act: -0.1700
Data Index: 7693158 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2139. Min Range: -8.2139
Max Act: 7.7764. Min Act: -0.1700
Data Index: 3120715 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2139. Min Range: -8.2139
Max Act: 7.7764. Min Act: -0.1700
Data Index: 7444808 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2139. Min Range: -8.2139
Max Act: 7.7764. Min Act: -0.1700
Data Index: 6566505 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2139. Min Range: -8.2139
Max Act: 7.7139. Min Act: -0.1700
Data Index: 2865700 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2139. Min Range: -8.2139
Max Act: 7.7139. Min Act: -0.1700
Data Index: 6991630 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2139. Min Range: -8.2139
Max Act: 7.7139. Min Act: -0.1700
Data Index: 93055 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #19