Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5532 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8700. Min Range: -7.8700
Max Act: 7.8700. Min Act: -0.1700
Data Index: 5606774 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8700. Min Range: -7.8700
Max Act: 7.3387. Min Act: -0.1700
Data Index: 1460463 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8700. Min Range: -7.8700
Max Act: 7.3075. Min Act: -0.1700
Data Index: 5296775 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8700. Min Range: -7.8700
Max Act: 7.2450. Min Act: -0.1700
Data Index: 5387470 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8700. Min Range: -7.8700
Max Act: 7.2450. Min Act: -0.1700
Data Index: 4011922 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8700. Min Range: -7.8700
Max Act: 7.1512. Min Act: -0.1700
Data Index: 1032435 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8700. Min Range: -7.8700
Max Act: 7.1825. Min Act: -0.1700
Data Index: 5301185 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8700. Min Range: -7.8700
Max Act: 7.1200. Min Act: -0.1700
Data Index: 4442619 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8700. Min Range: -7.8700
Max Act: 7.0887. Min Act: -0.1700
Data Index: 1957154 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8700. Min Range: -7.8700
Max Act: 7.0262. Min Act: -0.1700
Data Index: 1055120 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8700. Min Range: -7.8700
Max Act: 7.0262. Min Act: -0.1700
Data Index: 1066235 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8700. Min Range: -7.8700
Max Act: 6.9950. Min Act: -0.1700
Data Index: 3152096 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8700. Min Range: -7.8700
Max Act: 7.0262. Min Act: -0.1700
Data Index: 771360 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8700. Min Range: -7.8700
Max Act: 6.9950. Min Act: -0.1700
Data Index: 7821821 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8700. Min Range: -7.8700
Max Act: 6.9637. Min Act: -0.1700
Data Index: 6605583 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8700. Min Range: -7.8700
Max Act: 6.9325. Min Act: -0.1700
Data Index: 5782796 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8700. Min Range: -7.8700
Max Act: 6.9012. Min Act: -0.1700
Data Index: 7987662 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8700. Min Range: -7.8700
Max Act: 6.9325. Min Act: -0.1700
Data Index: 2655177 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8700. Min Range: -7.8700
Max Act: 6.9325. Min Act: -0.1700
Data Index: 874096 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8700. Min Range: -7.8700
Max Act: 6.9325. Min Act: -0.1700
Data Index: 7020127 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #19