Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3463 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7682. Min Range: -4.7682
Max Act: 4.7682. Min Act: -0.1700
Data Index: 2892308 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7682. Min Range: -4.7682
Max Act: 4.7057. Min Act: -0.1700
Data Index: 311635 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7682. Min Range: -4.7682
Max Act: 4.7057. Min Act: -0.1700
Data Index: 8019204 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7682. Min Range: -4.7682
Max Act: 4.7057. Min Act: -0.1700
Data Index: 7456386 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7682. Min Range: -4.7682
Max Act: 4.7057. Min Act: -0.1700
Data Index: 7474526 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7682. Min Range: -4.7682
Max Act: 4.7057. Min Act: -0.1700
Data Index: 1179064 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7682. Min Range: -4.7682
Max Act: 4.7057. Min Act: -0.1700
Data Index: 3665331 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7682. Min Range: -4.7682
Max Act: 4.7057. Min Act: -0.1700
Data Index: 7490784 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7682. Min Range: -4.7682
Max Act: 4.7057. Min Act: -0.1700
Data Index: 4716277 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7682. Min Range: -4.7682
Max Act: 4.7057. Min Act: -0.1700
Data Index: 8283570 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7682. Min Range: -4.7682
Max Act: 4.7057. Min Act: -0.1700
Data Index: 3234515 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7682. Min Range: -4.7682
Max Act: 4.7057. Min Act: -0.1700
Data Index: 133112 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7682. Min Range: -4.7682
Max Act: 4.7057. Min Act: -0.1700
Data Index: 3363570 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7682. Min Range: -4.7682
Max Act: 4.7057. Min Act: -0.1700
Data Index: 1093654 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7682. Min Range: -4.7682
Max Act: 4.7057. Min Act: -0.1700
Data Index: 1621490 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7682. Min Range: -4.7682
Max Act: 4.7057. Min Act: -0.1700
Data Index: 6249476 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7682. Min Range: -4.7682
Max Act: 4.7057. Min Act: -0.1700
Data Index: 8135939 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7682. Min Range: -4.7682
Max Act: 4.7057. Min Act: -0.1700
Data Index: 6649510 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7682. Min Range: -4.7682
Max Act: 4.4557. Min Act: -0.1700
Data Index: 1621488 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7682. Min Range: -4.7682
Max Act: 4.3932. Min Act: -0.1700
Data Index: 619845 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #19