Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3957 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9701. Min Range: -7.9701
Max Act: 7.9701. Min Act: -0.1700
Data Index: 6815802 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9701. Min Range: -7.9701
Max Act: 7.9701. Min Act: -0.1700
Data Index: 4025555 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9701. Min Range: -7.9701
Max Act: 7.7826. Min Act: -0.1700
Data Index: 4594065 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9701. Min Range: -7.9701
Max Act: 7.5639. Min Act: -0.1700
Data Index: 981101 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9701. Min Range: -7.9701
Max Act: 7.5014. Min Act: -0.1700
Data Index: 4666692 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9701. Min Range: -7.9701
Max Act: 7.5326. Min Act: -0.1700
Data Index: 248012 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9701. Min Range: -7.9701
Max Act: 7.4389. Min Act: -0.1700
Data Index: 4440104 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9701. Min Range: -7.9701
Max Act: 7.4076. Min Act: -0.1700
Data Index: 505342 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9701. Min Range: -7.9701
Max Act: 7.3451. Min Act: -0.1700
Data Index: 5257449 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9701. Min Range: -7.9701
Max Act: 7.2201. Min Act: -0.1700
Data Index: 4086007 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9701. Min Range: -7.9701
Max Act: 7.1889. Min Act: -0.1700
Data Index: 8811613 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9701. Min Range: -7.9701
Max Act: 7.1576. Min Act: -0.1700
Data Index: 5962431 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9701. Min Range: -7.9701
Max Act: 7.1576. Min Act: -0.1700
Data Index: 7155121 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9701. Min Range: -7.9701
Max Act: 7.1576. Min Act: -0.1700
Data Index: 4278173 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9701. Min Range: -7.9701
Max Act: 7.0951. Min Act: -0.1700
Data Index: 4399867 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9701. Min Range: -7.9701
Max Act: 7.0639. Min Act: -0.1700
Data Index: 2812609 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9701. Min Range: -7.9701
Max Act: 7.0951. Min Act: -0.1700
Data Index: 789418 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9701. Min Range: -7.9701
Max Act: 7.0639. Min Act: -0.1700
Data Index: 5164125 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9701. Min Range: -7.9701
Max Act: 7.0639. Min Act: -0.1700
Data Index: 2988789 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9701. Min Range: -7.9701
Max Act: 7.0639. Min Act: -0.1700
Data Index: 6440485 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #19