Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4422 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3766. Min Range: -5.3766
Max Act: 5.3766. Min Act: -0.1700
Data Index: 8605193 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3766. Min Range: -5.3766
Max Act: 5.2516. Min Act: -0.1700
Data Index: 811720 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3766. Min Range: -5.3766
Max Act: 5.1266. Min Act: -0.1700
Data Index: 6894228 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3766. Min Range: -5.3766
Max Act: 5.0954. Min Act: -0.1700
Data Index: 5148688 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3766. Min Range: -5.3766
Max Act: 5.0016. Min Act: -0.1700
Data Index: 528356 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3766. Min Range: -5.3766
Max Act: 5.0016. Min Act: -0.1700
Data Index: 5920465 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3766. Min Range: -5.3766
Max Act: 4.9704. Min Act: -0.1700
Data Index: 3678139 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3766. Min Range: -5.3766
Max Act: 4.9704. Min Act: -0.1700
Data Index: 5568828 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3766. Min Range: -5.3766
Max Act: 4.9391. Min Act: -0.1700
Data Index: 6171143 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3766. Min Range: -5.3766
Max Act: 4.9391. Min Act: -0.1700
Data Index: 4450464 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3766. Min Range: -5.3766
Max Act: 4.9079. Min Act: -0.1700
Data Index: 6411194 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3766. Min Range: -5.3766
Max Act: 4.9079. Min Act: -0.1700
Data Index: 6571890 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3766. Min Range: -5.3766
Max Act: 4.8766. Min Act: -0.1700
Data Index: 5402663 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3766. Min Range: -5.3766
Max Act: 4.8766. Min Act: -0.1700
Data Index: 8499052 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3766. Min Range: -5.3766
Max Act: 4.9079. Min Act: -0.1700
Data Index: 6381480 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3766. Min Range: -5.3766
Max Act: 4.8766. Min Act: -0.1700
Data Index: 5035808 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3766. Min Range: -5.3766
Max Act: 4.8454. Min Act: -0.1700
Data Index: 7971686 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3766. Min Range: -5.3766
Max Act: 4.8454. Min Act: -0.1700
Data Index: 7353500 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3766. Min Range: -5.3766
Max Act: 4.8454. Min Act: -0.1700
Data Index: 990945 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3766. Min Range: -5.3766
Max Act: 4.8454. Min Act: -0.1700
Data Index: 4566668 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #19