Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1375 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2855. Min Range: -6.2855
Max Act: 6.2855. Min Act: -0.1700
Data Index: 4704591 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2855. Min Range: -6.2855
Max Act: 6.2855. Min Act: -0.1700
Data Index: 5682942 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2855. Min Range: -6.2855
Max Act: 6.2230. Min Act: -0.1700
Data Index: 4189662 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2855. Min Range: -6.2855
Max Act: 6.1918. Min Act: -0.1700
Data Index: 121302 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2855. Min Range: -6.2855
Max Act: 6.1918. Min Act: -0.1700
Data Index: 1468524 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2855. Min Range: -6.2855
Max Act: 6.1605. Min Act: -0.1700
Data Index: 7078398 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2855. Min Range: -6.2855
Max Act: 6.1605. Min Act: -0.1699
Data Index: 7460062 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2855. Min Range: -6.2855
Max Act: 6.1605. Min Act: -0.1699
Data Index: 7573440 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2855. Min Range: -6.2855
Max Act: 6.1293. Min Act: -0.1700
Data Index: 6250957 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2855. Min Range: -6.2855
Max Act: 6.1605. Min Act: -0.1700
Data Index: 121307 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2855. Min Range: -6.2855
Max Act: 6.1293. Min Act: -0.1700
Data Index: 63386 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2855. Min Range: -6.2855
Max Act: 6.0980. Min Act: -0.1700
Data Index: 5193126 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2855. Min Range: -6.2855
Max Act: 6.0980. Min Act: -0.1697
Data Index: 8117543 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2855. Min Range: -6.2855
Max Act: 6.0980. Min Act: -0.1698
Data Index: 2760715 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2855. Min Range: -6.2855
Max Act: 6.0668. Min Act: -0.1699
Data Index: 4180003 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2855. Min Range: -6.2855
Max Act: 6.0668. Min Act: -0.1700
Data Index: 4976581 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2855. Min Range: -6.2855
Max Act: 6.0668. Min Act: -0.1700
Data Index: 3075703 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2855. Min Range: -6.2855
Max Act: 6.0668. Min Act: -0.1700
Data Index: 667874 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2855. Min Range: -6.2855
Max Act: 6.0668. Min Act: -0.1700
Data Index: 5708622 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2855. Min Range: -6.2855
Max Act: 6.0668. Min Act: -0.1700
Data Index: 4333224 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #19