Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4652 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9618. Min Range: -6.9618
Max Act: 6.9618. Min Act: -0.1700
Data Index: 6636139 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9618. Min Range: -6.9618
Max Act: 6.7430. Min Act: -0.1700
Data Index: 2040632 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9618. Min Range: -6.9618
Max Act: 6.6805. Min Act: -0.1700
Data Index: 3708627 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9618. Min Range: -6.9618
Max Act: 6.6805. Min Act: -0.1700
Data Index: 5248264 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9618. Min Range: -6.9618
Max Act: 6.5868. Min Act: -0.1700
Data Index: 6847701 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9618. Min Range: -6.9618
Max Act: 6.5555. Min Act: -0.1700
Data Index: 5820946 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9618. Min Range: -6.9618
Max Act: 6.4305. Min Act: -0.1700
Data Index: 138548 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9618. Min Range: -6.9618
Max Act: 6.4305. Min Act: -0.1700
Data Index: 7089736 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9618. Min Range: -6.9618
Max Act: 6.4305. Min Act: -0.1700
Data Index: 3825830 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9618. Min Range: -6.9618
Max Act: 6.4305. Min Act: -0.1700
Data Index: 391150 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9618. Min Range: -6.9618
Max Act: 6.4305. Min Act: -0.1700
Data Index: 2403698 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9618. Min Range: -6.9618
Max Act: 6.3993. Min Act: -0.1700
Data Index: 7518636 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9618. Min Range: -6.9618
Max Act: 6.3680. Min Act: -0.1700
Data Index: 4880251 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9618. Min Range: -6.9618
Max Act: 6.3993. Min Act: -0.1700
Data Index: 3856979 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9618. Min Range: -6.9618
Max Act: 6.3993. Min Act: -0.1700
Data Index: 6753337 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9618. Min Range: -6.9618
Max Act: 6.3993. Min Act: -0.1700
Data Index: 3949286 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9618. Min Range: -6.9618
Max Act: 6.3368. Min Act: -0.1700
Data Index: 2823457 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9618. Min Range: -6.9618
Max Act: 6.3368. Min Act: -0.1700
Data Index: 2985403 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9618. Min Range: -6.9618
Max Act: 6.3368. Min Act: -0.1700
Data Index: 5366334 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9618. Min Range: -6.9618
Max Act: 6.3055. Min Act: -0.1700
Data Index: 537278 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #19