Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3881 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7507. Min Range: -6.7507
Max Act: 6.7507. Min Act: -0.1700
Data Index: 5727970 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7507. Min Range: -6.7507
Max Act: 6.6882. Min Act: -0.1700
Data Index: 443119 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7507. Min Range: -6.7507
Max Act: 6.6257. Min Act: -0.1700
Data Index: 4730590 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7507. Min Range: -6.7507
Max Act: 6.6257. Min Act: -0.1700
Data Index: 137719 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7507. Min Range: -6.7507
Max Act: 6.5945. Min Act: -0.1700
Data Index: 780887 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7507. Min Range: -6.7507
Max Act: 6.5632. Min Act: -0.1700
Data Index: 1921140 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7507. Min Range: -6.7507
Max Act: 6.5007. Min Act: -0.1700
Data Index: 3624171 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7507. Min Range: -6.7507
Max Act: 6.5007. Min Act: -0.1700
Data Index: 242264 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7507. Min Range: -6.7507
Max Act: 6.4382. Min Act: -0.1700
Data Index: 7473137 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7507. Min Range: -6.7507
Max Act: 6.3757. Min Act: -0.1700
Data Index: 7580856 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7507. Min Range: -6.7507
Max Act: 6.3757. Min Act: -0.1700
Data Index: 3803372 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7507. Min Range: -6.7507
Max Act: 6.3757. Min Act: -0.1700
Data Index: 2283113 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7507. Min Range: -6.7507
Max Act: 6.4070. Min Act: -0.1700
Data Index: 4961549 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7507. Min Range: -6.7507
Max Act: 6.3757. Min Act: -0.1700
Data Index: 8606540 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7507. Min Range: -6.7507
Max Act: 6.3757. Min Act: -0.1700
Data Index: 4122165 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7507. Min Range: -6.7507
Max Act: 6.3132. Min Act: -0.1700
Data Index: 6144901 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7507. Min Range: -6.7507
Max Act: 6.3445. Min Act: -0.1700
Data Index: 272500 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7507. Min Range: -6.7507
Max Act: 6.3132. Min Act: -0.1700
Data Index: 3674123 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7507. Min Range: -6.7507
Max Act: 6.3132. Min Act: -0.1700
Data Index: 255879 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7507. Min Range: -6.7507
Max Act: 6.3132. Min Act: -0.1700
Data Index: 5245505 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #19