Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2595 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7454. Min Range: -6.7454
Max Act: 6.7454. Min Act: -0.1700
Data Index: 604843 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7454. Min Range: -6.7454
Max Act: 6.6517. Min Act: -0.1700
Data Index: 4687038 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7454. Min Range: -6.7454
Max Act: 6.5267. Min Act: -0.1700
Data Index: 7127843 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7454. Min Range: -6.7454
Max Act: 6.4954. Min Act: -0.1700
Data Index: 1303491 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7454. Min Range: -6.7454
Max Act: 6.4329. Min Act: -0.1700
Data Index: 2163547 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7454. Min Range: -6.7454
Max Act: 6.4329. Min Act: -0.1700
Data Index: 5903421 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7454. Min Range: -6.7454
Max Act: 6.4329. Min Act: -0.1700
Data Index: 6913692 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7454. Min Range: -6.7454
Max Act: 6.4017. Min Act: -0.1700
Data Index: 5761944 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7454. Min Range: -6.7454
Max Act: 6.4017. Min Act: -0.1700
Data Index: 2137739 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7454. Min Range: -6.7454
Max Act: 6.4017. Min Act: -0.1700
Data Index: 3075592 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7454. Min Range: -6.7454
Max Act: 6.4017. Min Act: -0.1700
Data Index: 6011514 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7454. Min Range: -6.7454
Max Act: 6.3704. Min Act: -0.1700
Data Index: 5606137 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7454. Min Range: -6.7454
Max Act: 6.3392. Min Act: -0.1700
Data Index: 8109480 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7454. Min Range: -6.7454
Max Act: 6.3079. Min Act: -0.1700
Data Index: 3550725 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7454. Min Range: -6.7454
Max Act: 6.3079. Min Act: -0.1700
Data Index: 7630707 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7454. Min Range: -6.7454
Max Act: 6.2454. Min Act: -0.1700
Data Index: 7075230 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7454. Min Range: -6.7454
Max Act: 6.2767. Min Act: -0.1700
Data Index: 504600 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7454. Min Range: -6.7454
Max Act: 6.2767. Min Act: -0.1700
Data Index: 833810 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7454. Min Range: -6.7454
Max Act: 6.2454. Min Act: -0.1700
Data Index: 116043 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7454. Min Range: -6.7454
Max Act: 6.2454. Min Act: -0.1700
Data Index: 6812118 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #19