Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3896 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4527. Min Range: -4.4527
Max Act: 4.4527. Min Act: -0.1700
Data Index: 3890203 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4527. Min Range: -4.4527
Max Act: 4.4527. Min Act: -0.1700
Data Index: 5874915 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4527. Min Range: -4.4527
Max Act: 4.3902. Min Act: -0.1700
Data Index: 7501201 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4527. Min Range: -4.4527
Max Act: 4.3902. Min Act: -0.1700
Data Index: 6561156 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4527. Min Range: -4.4527
Max Act: 4.3902. Min Act: -0.1700
Data Index: 3052004 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4527. Min Range: -4.4527
Max Act: 4.3902. Min Act: -0.1700
Data Index: 6331751 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4527. Min Range: -4.4527
Max Act: 4.3902. Min Act: -0.1700
Data Index: 208690 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4527. Min Range: -4.4527
Max Act: 4.3590. Min Act: -0.1700
Data Index: 5345161 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4527. Min Range: -4.4527
Max Act: 4.3902. Min Act: -0.1700
Data Index: 7883506 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4527. Min Range: -4.4527
Max Act: 4.3902. Min Act: -0.1700
Data Index: 7741031 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4527. Min Range: -4.4527
Max Act: 4.3902. Min Act: -0.1700
Data Index: 2108380 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4527. Min Range: -4.4527
Max Act: 4.3590. Min Act: -0.1700
Data Index: 184264 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4527. Min Range: -4.4527
Max Act: 4.3590. Min Act: -0.1700
Data Index: 5581216 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4527. Min Range: -4.4527
Max Act: 4.3590. Min Act: -0.1700
Data Index: 5608672 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4527. Min Range: -4.4527
Max Act: 4.3590. Min Act: -0.1700
Data Index: 2765271 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4527. Min Range: -4.4527
Max Act: 4.3590. Min Act: -0.1700
Data Index: 6082083 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4527. Min Range: -4.4527
Max Act: 4.3590. Min Act: -0.1700
Data Index: 1067445 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4527. Min Range: -4.4527
Max Act: 4.3590. Min Act: -0.1700
Data Index: 1456372 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4527. Min Range: -4.4527
Max Act: 4.3590. Min Act: -0.1700
Data Index: 3073475 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4527. Min Range: -4.4527
Max Act: 4.3590. Min Act: -0.1700
Data Index: 3291105 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19