Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4725 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2721. Min Range: -4.2721
Max Act: 4.2721. Min Act: -0.1700
Data Index: 7766251 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2721. Min Range: -4.2721
Max Act: 4.2721. Min Act: -0.1700
Data Index: 3526665 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2721. Min Range: -4.2721
Max Act: 4.2096. Min Act: -0.1700
Data Index: 2369778 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2721. Min Range: -4.2721
Max Act: 4.1783. Min Act: -0.1700
Data Index: 4323564 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2721. Min Range: -4.2721
Max Act: 4.1158. Min Act: -0.1700
Data Index: 399152 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2721. Min Range: -4.2721
Max Act: 4.0533. Min Act: -0.1700
Data Index: 7204249 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2721. Min Range: -4.2721
Max Act: 4.0220. Min Act: -0.1700
Data Index: 2714167 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2721. Min Range: -4.2721
Max Act: 4.0220. Min Act: -0.1700
Data Index: 2311527 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2721. Min Range: -4.2721
Max Act: 4.0220. Min Act: -0.1700
Data Index: 3123243 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2721. Min Range: -4.2721
Max Act: 3.9908. Min Act: -0.1700
Data Index: 3216884 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2721. Min Range: -4.2721
Max Act: 4.0533. Min Act: -0.1700
Data Index: 1571975 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2721. Min Range: -4.2721
Max Act: 3.9908. Min Act: -0.1700
Data Index: 2208556 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2721. Min Range: -4.2721
Max Act: 3.9595. Min Act: -0.1700
Data Index: 2920132 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2721. Min Range: -4.2721
Max Act: 3.9908. Min Act: -0.1700
Data Index: 4115186 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2721. Min Range: -4.2721
Max Act: 3.9908. Min Act: -0.1700
Data Index: 2048201 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2721. Min Range: -4.2721
Max Act: 3.9595. Min Act: -0.1700
Data Index: 3850025 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2721. Min Range: -4.2721
Max Act: 3.9595. Min Act: -0.1700
Data Index: 1222904 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2721. Min Range: -4.2721
Max Act: 3.9595. Min Act: -0.1700
Data Index: 336933 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2721. Min Range: -4.2721
Max Act: 3.9595. Min Act: -0.1700
Data Index: 336028 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2721. Min Range: -4.2721
Max Act: 3.9595. Min Act: -0.1700
Data Index: 7060730 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #19