Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2976 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5703. Min Range: -5.5703
Max Act: 5.5703. Min Act: -0.1700
Data Index: 3518484 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5703. Min Range: -5.5703
Max Act: 5.2890. Min Act: -0.1700
Data Index: 6134423 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5703. Min Range: -5.5703
Max Act: 5.2890. Min Act: -0.1700
Data Index: 5246452 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5703. Min Range: -5.5703
Max Act: 5.2265. Min Act: -0.1700
Data Index: 2113128 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5703. Min Range: -5.5703
Max Act: 5.1015. Min Act: -0.1700
Data Index: 5319749 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5703. Min Range: -5.5703
Max Act: 4.9765. Min Act: -0.1700
Data Index: 8321784 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5703. Min Range: -5.5703
Max Act: 4.9765. Min Act: -0.1700
Data Index: 5654552 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5703. Min Range: -5.5703
Max Act: 4.9765. Min Act: -0.1700
Data Index: 3958689 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5703. Min Range: -5.5703
Max Act: 4.9453. Min Act: -0.1700
Data Index: 3846519 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5703. Min Range: -5.5703
Max Act: 4.9453. Min Act: -0.1700
Data Index: 4854834 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5703. Min Range: -5.5703
Max Act: 4.9140. Min Act: -0.1700
Data Index: 3621927 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5703. Min Range: -5.5703
Max Act: 4.8828. Min Act: -0.1700
Data Index: 6129167 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5703. Min Range: -5.5703
Max Act: 4.8828. Min Act: -0.1700
Data Index: 3950904 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5703. Min Range: -5.5703
Max Act: 4.8828. Min Act: -0.1700
Data Index: 4489166 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5703. Min Range: -5.5703
Max Act: 4.8828. Min Act: -0.1700
Data Index: 2613770 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5703. Min Range: -5.5703
Max Act: 4.8828. Min Act: -0.1700
Data Index: 89673 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5703. Min Range: -5.5703
Max Act: 4.8828. Min Act: -0.1700
Data Index: 5783854 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5703. Min Range: -5.5703
Max Act: 4.8515. Min Act: -0.1700
Data Index: 5629069 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5703. Min Range: -5.5703
Max Act: 4.8515. Min Act: -0.1700
Data Index: 3238423 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5703. Min Range: -5.5703
Max Act: 4.8515. Min Act: -0.1700
Data Index: 6186238 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #19