Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5027 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7516. Min Range: -3.7516
Max Act: 3.7516. Min Act: -0.1700
Data Index: 300599 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7516. Min Range: -3.7516
Max Act: 3.6734. Min Act: -0.1700
Data Index: 8208152 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7516. Min Range: -3.7516
Max Act: 3.6734. Min Act: -0.1700
Data Index: 792182 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7516. Min Range: -3.7516
Max Act: 3.6264. Min Act: -0.1700
Data Index: 8375035 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7516. Min Range: -3.7516
Max Act: 3.6264. Min Act: -0.1700
Data Index: 2301675 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7516. Min Range: -3.7516
Max Act: 3.6421. Min Act: -0.1700
Data Index: 5260374 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7516. Min Range: -3.7516
Max Act: 3.6421. Min Act: -0.1700
Data Index: 7062604 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7516. Min Range: -3.7516
Max Act: 3.5951. Min Act: -0.1700
Data Index: 3195593 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7516. Min Range: -3.7516
Max Act: 3.5951. Min Act: -0.1700
Data Index: 2476713 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7516. Min Range: -3.7516
Max Act: 3.5638. Min Act: -0.1700
Data Index: 1054712 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7516. Min Range: -3.7516
Max Act: 3.5795. Min Act: -0.1700
Data Index: 906389 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7516. Min Range: -3.7516
Max Act: 3.5638. Min Act: -0.1700
Data Index: 7443093 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7516. Min Range: -3.7516
Max Act: 3.5638. Min Act: -0.1700
Data Index: 180087 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7516. Min Range: -3.7516
Max Act: 3.5638. Min Act: -0.1700
Data Index: 2870837 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7516. Min Range: -3.7516
Max Act: 3.5638. Min Act: -0.1700
Data Index: 3864760 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7516. Min Range: -3.7516
Max Act: 3.5482. Min Act: -0.1700
Data Index: 6879726 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7516. Min Range: -3.7516
Max Act: 3.5325. Min Act: -0.1700
Data Index: 7410901 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7516. Min Range: -3.7516
Max Act: 3.5325. Min Act: -0.1700
Data Index: 6824399 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7516. Min Range: -3.7516
Max Act: 3.5325. Min Act: -0.1700
Data Index: 7113835 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7516. Min Range: -3.7516
Max Act: 3.5325. Min Act: -0.1700
Data Index: 7935529 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #19