Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3915 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6581. Min Range: -6.6581
Max Act: 6.6581. Min Act: -0.1700
Data Index: 4497781 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6581. Min Range: -6.6581
Max Act: 6.6268. Min Act: -0.1700
Data Index: 1440639 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6581. Min Range: -6.6581
Max Act: 6.5018. Min Act: -0.1700
Data Index: 8759131 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6581. Min Range: -6.6581
Max Act: 6.5018. Min Act: -0.1700
Data Index: 4230708 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6581. Min Range: -6.6581
Max Act: 6.4706. Min Act: -0.1700
Data Index: 5060687 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6581. Min Range: -6.6581
Max Act: 6.4706. Min Act: -0.1700
Data Index: 3424523 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6581. Min Range: -6.6581
Max Act: 6.4706. Min Act: -0.1700
Data Index: 3436753 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6581. Min Range: -6.6581
Max Act: 6.4706. Min Act: -0.1700
Data Index: 1652783 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6581. Min Range: -6.6581
Max Act: 6.4393. Min Act: -0.1700
Data Index: 244151 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6581. Min Range: -6.6581
Max Act: 6.4393. Min Act: -0.1700
Data Index: 937831 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6581. Min Range: -6.6581
Max Act: 6.4081. Min Act: -0.1700
Data Index: 6315993 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6581. Min Range: -6.6581
Max Act: 6.4081. Min Act: -0.1700
Data Index: 1919063 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6581. Min Range: -6.6581
Max Act: 6.3768. Min Act: -0.1700
Data Index: 293756 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6581. Min Range: -6.6581
Max Act: 6.3768. Min Act: -0.1700
Data Index: 3948619 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6581. Min Range: -6.6581
Max Act: 6.3768. Min Act: -0.1700
Data Index: 636298 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6581. Min Range: -6.6581
Max Act: 6.3456. Min Act: -0.1700
Data Index: 2660653 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6581. Min Range: -6.6581
Max Act: 6.3456. Min Act: -0.1700
Data Index: 2897962 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6581. Min Range: -6.6581
Max Act: 6.3456. Min Act: -0.1700
Data Index: 1402122 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6581. Min Range: -6.6581
Max Act: 6.3456. Min Act: -0.1700
Data Index: 3590580 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6581. Min Range: -6.6581
Max Act: 6.3456. Min Act: -0.1700
Data Index: 3677588 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #19